diff --git a/Gemfile b/Gemfile index 8c0bb82a5..dfcdb3e30 100644 --- a/Gemfile +++ b/Gemfile @@ -195,10 +195,10 @@ gem 'reverse_markdown' gem 'iso-639' gem 'ruby-openai' -gem 'ai-agents', '>= 0.9.1' +gem 'ai-agents', '>= 0.10.0' # TODO: Move this gem as a dependency of ai-agents -gem 'ruby_llm', '>= 1.8.2' +gem 'ruby_llm', '>= 1.14.1' gem 'ruby_llm-schema' gem 'cld3', '~> 3.7' diff --git a/Gemfile.lock b/Gemfile.lock index bd21b7a36..15d9b2614 100644 --- a/Gemfile.lock +++ b/Gemfile.lock @@ -126,8 +126,8 @@ GEM jbuilder (~> 2) rails (>= 4.2, < 7.2) selectize-rails (~> 0.6) - ai-agents (0.9.1) - ruby_llm (~> 1.9.1) + ai-agents (0.10.0) + ruby_llm (~> 1.14) annotaterb (4.20.0) activerecord (>= 6.0.0) activesupport (>= 6.0.0) @@ -307,8 +307,8 @@ GEM faraday-mashify (1.0.0) faraday (~> 2.0) hashie - faraday-multipart (1.0.4) - multipart-post (~> 2) + faraday-multipart (1.2.0) + multipart-post (~> 2.0) faraday-net_http (3.4.2) net-http (~> 0.5) faraday-net_http_persistent (2.1.0) @@ -466,7 +466,7 @@ GEM rails-dom-testing (>= 1, < 3) railties (>= 4.2.0) thor (>= 0.14, < 2.0) - json (2.19.2) + json (2.19.5) json_refs (0.1.8) hana json_schemer (0.2.24) @@ -835,17 +835,17 @@ GEM ruby2ruby (2.5.0) ruby_parser (~> 3.1) sexp_processor (~> 4.6) - ruby_llm (1.9.2) + ruby_llm (1.15.0) base64 event_stream_parser (~> 1) faraday (>= 1.10.0) faraday-multipart (>= 1) faraday-net_http (>= 1) faraday-retry (>= 1) - marcel (~> 1.0) - ruby_llm-schema (~> 0.2.1) + marcel (~> 1) + ruby_llm-schema (~> 0) zeitwerk (~> 2) - ruby_llm-schema (0.2.5) + ruby_llm-schema (0.3.0) ruby_parser (3.20.0) sexp_processor (~> 4.16) sass (3.7.4) @@ -1019,7 +1019,7 @@ GEM working_hours (1.4.1) activesupport (>= 3.2) tzinfo - zeitwerk (2.7.4) + zeitwerk (2.7.5) PLATFORMS arm64-darwin-20 @@ -1039,7 +1039,7 @@ DEPENDENCIES administrate (>= 0.20.1) administrate-field-active_storage (>= 1.0.3) administrate-field-belongs_to_search (>= 0.9.0) - ai-agents (>= 0.9.1) + ai-agents (>= 0.10.0) annotaterb attr_extras audited (~> 5.4, >= 5.4.1) @@ -1144,7 +1144,7 @@ DEPENDENCIES rubocop-rails rubocop-rspec ruby-openai - ruby_llm (>= 1.8.2) + ruby_llm (>= 1.14.1) ruby_llm-schema scout_apm scss_lint diff --git a/config/llm_models.json b/config/llm_models.json index e2fe0e938..00c2038e5 100644 --- a/config/llm_models.json +++ b/config/llm_models.json @@ -4,7 +4,7 @@ "name": "Claude Haiku 3.5", "provider": "anthropic", "family": "claude-haiku", - "created_at": "2024-10-22 00:00:00 +0530", + "created_at": "2024-10-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": "2024-07-31", @@ -27,7 +27,8 @@ "standard": { "input_per_million": 0.8, "output_per_million": 4, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08, + "cache_write_input_per_million": 1 } } }, @@ -56,7 +57,7 @@ "name": "Claude Haiku 3.5 (latest)", "provider": "anthropic", "family": "claude-haiku", - "created_at": "2024-10-22 00:00:00 +0530", + "created_at": "2024-10-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": "2024-07-31", @@ -79,7 +80,8 @@ "standard": { "input_per_million": 0.8, "output_per_million": 4, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08, + "cache_write_input_per_million": 1 } } }, @@ -108,7 +110,7 @@ "name": "Claude Sonnet 3.5", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2024-06-20 00:00:00 +0530", + "created_at": "2024-06-20 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": "2024-04-30", @@ -131,7 +133,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -160,7 +163,7 @@ "name": "Claude Sonnet 3.5 v2", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2024-10-22 00:00:00 +0530", + "created_at": "2024-10-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": "2024-04-30", @@ -183,7 +186,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -212,7 +216,7 @@ "name": "Claude Sonnet 3.7", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2025-02-19 00:00:00 +0530", + "created_at": "2025-02-19 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2024-10-31", @@ -236,7 +240,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -265,7 +270,7 @@ "name": "Claude Haiku 3", "provider": "anthropic", "family": "claude-haiku", - "created_at": "2024-03-13 00:00:00 +0530", + "created_at": "2024-03-13 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 4096, "knowledge_cutoff": "2023-08-31", @@ -288,7 +293,8 @@ "standard": { "input_per_million": 0.25, "output_per_million": 1.25, - "cached_input_per_million": 0.03 + "cache_read_input_per_million": 0.03, + "cache_write_input_per_million": 0.3 } } }, @@ -317,7 +323,7 @@ "name": "Claude Opus 3", "provider": "anthropic", "family": "claude-opus", - "created_at": "2024-02-29 00:00:00 +0530", + "created_at": "2024-02-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 4096, "knowledge_cutoff": "2023-08-31", @@ -340,7 +346,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -369,7 +376,7 @@ "name": "Claude Sonnet 3", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2024-03-04 00:00:00 +0530", + "created_at": "2024-03-04 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 4096, "knowledge_cutoff": "2023-08-31", @@ -392,7 +399,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 0.3 } } }, @@ -421,7 +429,7 @@ "name": "Claude Haiku 4.5 (latest)", "provider": "anthropic", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -445,7 +453,8 @@ "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, @@ -474,7 +483,7 @@ "name": "Claude Haiku 4.5", "provider": "anthropic", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -498,7 +507,8 @@ "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, @@ -527,7 +537,7 @@ "name": "Claude Opus 4 (latest)", "provider": "anthropic", "family": "claude-opus", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -551,7 +561,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -580,7 +591,7 @@ "name": "Claude Opus 4.1 (latest)", "provider": "anthropic", "family": "claude-opus", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -604,7 +615,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -633,7 +645,7 @@ "name": "Claude Opus 4.1", "provider": "anthropic", "family": "claude-opus", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -657,7 +669,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -686,7 +699,7 @@ "name": "Claude Opus 4", "provider": "anthropic", "family": "claude-opus", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -710,7 +723,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -739,7 +753,7 @@ "name": "Claude Opus 4.5 (latest)", "provider": "anthropic", "family": "claude-opus", - "created_at": "2025-11-24 00:00:00 +0530", + "created_at": "2025-11-24 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -763,7 +777,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -792,7 +807,7 @@ "name": "Claude Opus 4.5", "provider": "anthropic", "family": "claude-opus", - "created_at": "2025-11-01 00:00:00 +0530", + "created_at": "2025-11-01 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -816,7 +831,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -845,10 +861,10 @@ "name": "Claude Opus 4.6", "provider": "anthropic", "family": "claude-opus", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", @@ -869,7 +885,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -890,7 +907,61 @@ "context": 1000000, "output": 128000 }, - "knowledge": "2025-05" + "knowledge": "2025-05-31" + } + }, + { + "id": "claude-opus-4-7", + "name": "Claude Opus 4.7", + "provider": "anthropic", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "anthropic", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" } }, { @@ -898,7 +969,7 @@ "name": "Claude Sonnet 4 (latest)", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -922,7 +993,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -951,7 +1023,7 @@ "name": "Claude Sonnet 4", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -975,7 +1047,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1004,7 +1077,7 @@ "name": "Claude Sonnet 4.5 (latest)", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -1028,7 +1101,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1057,7 +1131,7 @@ "name": "Claude Sonnet 4.5", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -1081,7 +1155,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1110,10 +1185,10 @@ "name": "Claude Sonnet 4.6", "provider": "anthropic", "family": "claude-sonnet", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", @@ -1134,7 +1209,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1155,7 +1231,8577 @@ "context": 1000000, "output": 64000 }, - "knowledge": "2025-08" + "knowledge": "2025-08-31" + } + }, + { + "id": "AI21-Jamba-1.5-Large", + "name": "AI21-Jamba-1.5-Large", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "AI21-Jamba-1.5-Mini", + "name": "AI21-Jamba-1.5-Mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "AI21-Jamba-Instruct", + "name": "AI21-Jamba-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Codestral-2501-2", + "name": "Codestral-2501-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-command-r", + "name": "Cohere-command-r", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-command-r-08-2024", + "name": "Cohere-command-r-08-2024", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-command-r-plus", + "name": "Cohere-command-r-plus", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-command-r-plus-08-2024", + "name": "Cohere-command-r-plus-08-2024", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-embed-v3-english", + "name": "Cohere-embed-v3-english", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-embed-v3-multilingual", + "name": "Cohere-embed-v3-multilingual", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-rerank-v4.0-fast", + "name": "Cohere-rerank-v4.0-fast", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Cohere-rerank-v4.0-pro", + "name": "Cohere-rerank-v4.0-pro", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-R1", + "name": "DeepSeek-R1", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-R1-0528", + "name": "DeepSeek-R1-0528", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-V3", + "name": "DeepSeek-V3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-V3-0324", + "name": "DeepSeek-V3-0324", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-V3.1", + "name": "DeepSeek-V3.1", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-V3.2", + "name": "DeepSeek-V3.2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-V3.2-Speciale", + "name": "DeepSeek-V3.2-Speciale", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "DeepSeek-V4-Flash-2026-04-23", + "name": "DeepSeek-V4-Flash-2026-04-23", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "FLUX-1.1-pro", + "name": "FLUX-1.1-pro", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "FLUX.1-Kontext-pro", + "name": "FLUX.1-Kontext-pro", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "FLUX.2-pro", + "name": "FLUX.2-pro", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Kimi-K2-Thinking", + "name": "Kimi-K2-Thinking", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Kimi-K2.5", + "name": "Kimi-K2.5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Kimi-K2.6-2026-04-20", + "name": "Kimi-K2.6-2026-04-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.2-11B-Vision-Instruct", + "name": "Llama-3.2-11B-Vision-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.2-11B-Vision-Instruct-2", + "name": "Llama-3.2-11B-Vision-Instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.2-90B-Vision-Instruct", + "name": "Llama-3.2-90B-Vision-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.2-90B-Vision-Instruct-2", + "name": "Llama-3.2-90B-Vision-Instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.2-90B-Vision-Instruct-3", + "name": "Llama-3.2-90B-Vision-Instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.3-70B-Instruct", + "name": "Llama-3.3-70B-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.3-70B-Instruct-2", + "name": "Llama-3.3-70B-Instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.3-70B-Instruct-3", + "name": "Llama-3.3-70B-Instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.3-70B-Instruct-4", + "name": "Llama-3.3-70B-Instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.3-70B-Instruct-5", + "name": "Llama-3.3-70B-Instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-3.3-70B-Instruct-9", + "name": "Llama-3.3-70B-Instruct-9", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-4-Maverick-17B-128E-Instruct-FP8", + "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Llama-4-Scout-17B-16E-Instruct", + "name": "Llama-4-Scout-17B-16E-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "MAI-DS-R1", + "name": "MAI-DS-R1", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "MAI-Image-2-2026-02-20", + "name": "MAI-Image-2-2026-02-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "MAI-Image-2e-2026-04-09", + "name": "MAI-Image-2e-2026-04-09", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-70B-Instruct-6", + "name": "Meta-Llama-3-70B-Instruct-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-70B-Instruct-7", + "name": "Meta-Llama-3-70B-Instruct-7", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-70B-Instruct-8", + "name": "Meta-Llama-3-70B-Instruct-8", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-70B-Instruct-9", + "name": "Meta-Llama-3-70B-Instruct-9", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-8B-Instruct-6", + "name": "Meta-Llama-3-8B-Instruct-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-8B-Instruct-7", + "name": "Meta-Llama-3-8B-Instruct-7", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-8B-Instruct-8", + "name": "Meta-Llama-3-8B-Instruct-8", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3-8B-Instruct-9", + "name": "Meta-Llama-3-8B-Instruct-9", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-405B-Instruct", + "name": "Meta-Llama-3.1-405B-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-70B-Instruct", + "name": "Meta-Llama-3.1-70B-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-70B-Instruct-2", + "name": "Meta-Llama-3.1-70B-Instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-70B-Instruct-3", + "name": "Meta-Llama-3.1-70B-Instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-70B-Instruct-4", + "name": "Meta-Llama-3.1-70B-Instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-8B-Instruct", + "name": "Meta-Llama-3.1-8B-Instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-8B-Instruct-2", + "name": "Meta-Llama-3.1-8B-Instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-8B-Instruct-3", + "name": "Meta-Llama-3.1-8B-Instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-8B-Instruct-4", + "name": "Meta-Llama-3.1-8B-Instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Meta-Llama-3.1-8B-Instruct-5", + "name": "Meta-Llama-3.1-8B-Instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Ministral-3B", + "name": "Ministral-3B", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Mistral-Large-2411-2", + "name": "Mistral-Large-2411-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Mistral-Large-3", + "name": "Mistral-Large-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Mistral-Nemo", + "name": "Mistral-Nemo", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Mistral-large", + "name": "Mistral-large", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Mistral-large-2407", + "name": "Mistral-large-2407", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Mistral-small", + "name": "Mistral-small", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-128k-instruct-3", + "name": "Phi-3-medium-128k-instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-128k-instruct-4", + "name": "Phi-3-medium-128k-instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-128k-instruct-5", + "name": "Phi-3-medium-128k-instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-128k-instruct-6", + "name": "Phi-3-medium-128k-instruct-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-128k-instruct-7", + "name": "Phi-3-medium-128k-instruct-7", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-4k-instruct-3", + "name": "Phi-3-medium-4k-instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-4k-instruct-4", + "name": "Phi-3-medium-4k-instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-4k-instruct-5", + "name": "Phi-3-medium-4k-instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-medium-4k-instruct-6", + "name": "Phi-3-medium-4k-instruct-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-128k-instruct-10", + "name": "Phi-3-mini-128k-instruct-10", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-128k-instruct-11", + "name": "Phi-3-mini-128k-instruct-11", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-128k-instruct-12", + "name": "Phi-3-mini-128k-instruct-12", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-128k-instruct-13", + "name": "Phi-3-mini-128k-instruct-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-4k-instruct-10", + "name": "Phi-3-mini-4k-instruct-10", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-4k-instruct-11", + "name": "Phi-3-mini-4k-instruct-11", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-4k-instruct-13", + "name": "Phi-3-mini-4k-instruct-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-4k-instruct-14", + "name": "Phi-3-mini-4k-instruct-14", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-mini-4k-instruct-15", + "name": "Phi-3-mini-4k-instruct-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-small-128k-instruct-3", + "name": "Phi-3-small-128k-instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-small-128k-instruct-4", + "name": "Phi-3-small-128k-instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-small-128k-instruct-5", + "name": "Phi-3-small-128k-instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-small-8k-instruct-3", + "name": "Phi-3-small-8k-instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-small-8k-instruct-4", + "name": "Phi-3-small-8k-instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3-small-8k-instruct-5", + "name": "Phi-3-small-8k-instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-MoE-instruct-2", + "name": "Phi-3.5-MoE-instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-MoE-instruct-3", + "name": "Phi-3.5-MoE-instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-MoE-instruct-4", + "name": "Phi-3.5-MoE-instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-MoE-instruct-5", + "name": "Phi-3.5-MoE-instruct-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-mini-instruct", + "name": "Phi-3.5-mini-instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-mini-instruct-2", + "name": "Phi-3.5-mini-instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-mini-instruct-3", + "name": "Phi-3.5-mini-instruct-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-mini-instruct-4", + "name": "Phi-3.5-mini-instruct-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-mini-instruct-6", + "name": "Phi-3.5-mini-instruct-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-vision-instruct", + "name": "Phi-3.5-vision-instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-3.5-vision-instruct-2", + "name": "Phi-3.5-vision-instruct-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-2", + "name": "Phi-4-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-3", + "name": "Phi-4-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-4", + "name": "Phi-4-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-5", + "name": "Phi-4-5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-6", + "name": "Phi-4-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-7", + "name": "Phi-4-7", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-mini-instruct", + "name": "Phi-4-mini-instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-mini-reasoning", + "name": "Phi-4-mini-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-multimodal-instruct", + "name": "Phi-4-multimodal-instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Phi-4-reasoning", + "name": "Phi-4-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Stable-Diffusion-3.5-Large", + "name": "Stable-Diffusion-3.5-Large", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Stable-Image-Core", + "name": "Stable-Image-Core", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "Stable-Image-Ultra", + "name": "Stable-Image-Ultra", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "ada", + "name": "ada", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "aoai-sora", + "name": "aoai-sora", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "aoai-sora-2025-02-28", + "name": "aoai-sora-2025-02-28", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "babbage", + "name": "babbage", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.4, + "output_per_million": 0.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-haiku-4-5-20251001", + "name": "claude-haiku-4-5-20251001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-opus-4-1-20250805", + "name": "claude-opus-4-1-20250805", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-opus-4-5-20251101", + "name": "claude-opus-4-5-20251101", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-opus-4-6", + "name": "claude-opus-4-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-opus-4-7", + "name": "claude-opus-4-7", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-sonnet-4-5-20250929", + "name": "claude-sonnet-4-5-20250929", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "claude-sonnet-4-6", + "name": "claude-sonnet-4-6", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-cushman-001", + "name": "code-cushman-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-cushman-fine-tune-002", + "name": "code-cushman-fine-tune-002", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-davinci-002", + "name": "code-davinci-002", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-davinci-fine-tune-002", + "name": "code-davinci-fine-tune-002", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-search-ada-code-001", + "name": "code-search-ada-code-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-search-ada-text-001", + "name": "code-search-ada-text-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-search-babbage-code-001", + "name": "code-search-babbage-code-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "code-search-babbage-text-001", + "name": "code-search-babbage-text-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "codex-mini-2025-05-16", + "name": "codex-mini-2025-05-16", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "cohere-command-a", + "name": "cohere-command-a", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "computer-use-preview-2025-04-15", + "name": "computer-use-preview-2025-04-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "curie", + "name": "curie", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "dall-e-2", + "name": "dall-e-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "dall-e-2-2.0", + "name": "dall-e-2-2.0", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "dall-e-3", + "name": "dall-e-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "dall-e-3-3.0", + "name": "dall-e-3-3.0", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "davinci", + "name": "davinci", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 2.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "embed-v-4-0", + "name": "embed-v-4-0", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo", + "name": "gpt-35-turbo", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-0125", + "name": "gpt-35-turbo-0125", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-0301", + "name": "gpt-35-turbo-0301", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-0613", + "name": "gpt-35-turbo-0613", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-1106", + "name": "gpt-35-turbo-1106", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-16k", + "name": "gpt-35-turbo-16k", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-16k-0613", + "name": "gpt-35-turbo-16k-0613", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-instruct", + "name": "gpt-35-turbo-instruct", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-35-turbo-instruct-0914", + "name": "gpt-35-turbo-instruct-0914", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4", + "name": "gpt-4", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 8192, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 30.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-0125-Preview", + "name": "gpt-4-0125-Preview", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-0314", + "name": "gpt-4-0314", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-0613", + "name": "gpt-4-0613", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-1106-Preview", + "name": "gpt-4-1106-Preview", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-32k", + "name": "gpt-4-32k", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-32k-0314", + "name": "gpt-4-32k-0314", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-32k-0613", + "name": "gpt-4-32k-0613", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-turbo-2024-04-09", + "name": "gpt-4-turbo-2024-04-09", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 30.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-turbo-jp", + "name": "gpt-4-turbo-jp", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 30.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4-vision-preview", + "name": "gpt-4-vision-preview", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1", + "name": "gpt-4.1", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1-2025-04-14", + "name": "gpt-4.1-2025-04-14", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1-2025-04-14-text", + "name": "gpt-4.1-2025-04-14-text", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1-mini", + "name": "gpt-4.1-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.4, + "output_per_million": 1.6, + "cache_read_input_per_million": 0.1 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1-mini-2025-04-14", + "name": "gpt-4.1-mini-2025-04-14", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.4, + "output_per_million": 1.6, + "cache_read_input_per_million": 0.1 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1-nano", + "name": "gpt-4.1-nano", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4.1-nano-2025-04-14", + "name": "gpt-4.1-nano-2025-04-14", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o", + "name": "gpt-4o", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-2024-05-13", + "name": "gpt-4o-2024-05-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-2024-08-06", + "name": "gpt-4o-2024-08-06", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-2024-11-20", + "name": "gpt-4o-2024-11-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-audio-mai", + "name": "gpt-4o-audio-mai", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-audio-preview-2024-10-01", + "name": "gpt-4o-audio-preview-2024-10-01", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-audio-preview-2024-12-17", + "name": "gpt-4o-audio-preview-2024-12-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-audio-preview-2025-06-03", + "name": "gpt-4o-audio-preview-2025-06-03", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-canvas-2024-09-25", + "name": "gpt-4o-canvas-2024-09-25", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini", + "name": "gpt-4o-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-2024-07-18", + "name": "gpt-4o-mini-2024-07-18", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-audio-preview-2024-12-17", + "name": "gpt-4o-mini-audio-preview-2024-12-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-realtime-preview-2024-12-17", + "name": "gpt-4o-mini-realtime-preview-2024-12-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 2.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-transcribe", + "name": "gpt-4o-mini-transcribe", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 16000, + "max_output_tokens": 2000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 5.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-transcribe-2025-03-20", + "name": "gpt-4o-mini-transcribe-2025-03-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 16000, + "max_output_tokens": 2000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 5.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-transcribe-2025-12-15", + "name": "gpt-4o-mini-transcribe-2025-12-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 16000, + "max_output_tokens": 2000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 5.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-tts", + "name": "gpt-4o-mini-tts", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 12.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-tts-2025-03-20", + "name": "gpt-4o-mini-tts-2025-03-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 12.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-mini-tts-2025-12-15", + "name": "gpt-4o-mini-tts-2025-12-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 12.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-realtime-preview", + "name": "gpt-4o-realtime-preview", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 20.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-realtime-preview-2024-12-17", + "name": "gpt-4o-realtime-preview-2024-12-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 20.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-realtime-preview-2025-06-03", + "name": "gpt-4o-realtime-preview-2025-06-03", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 20.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-transcribe", + "name": "gpt-4o-transcribe", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-transcribe-2025-03-20", + "name": "gpt-4o-transcribe-2025-03-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-transcribe-diarize", + "name": "gpt-4o-transcribe-diarize", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-4o-transcribe-diarize-2025-10-15", + "name": "gpt-4o-transcribe-diarize-2025-10-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-2025-08-07", + "name": "gpt-5-2025-08-07", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-chat-2025-08-07", + "name": "gpt-5-chat-2025-08-07", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-chat-2025-08-15", + "name": "gpt-5-chat-2025-08-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-chat-2025-10-03", + "name": "gpt-5-chat-2025-10-03", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-codex-2025-09-15", + "name": "gpt-5-codex-2025-09-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-mini-2025-08-07", + "name": "gpt-5-mini-2025-08-07", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-mini-2025-08-07-lite", + "name": "gpt-5-mini-2025-08-07-lite", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-mini-lite-2025-08-07", + "name": "gpt-5-mini-lite-2025-08-07", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-nano-2025-08-07", + "name": "gpt-5-nano-2025-08-07", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.05, + "output_per_million": 0.4, + "cache_read_input_per_million": 0.005 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5-pro-2025-10-06", + "name": "gpt-5-pro-2025-10-06", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.1", + "name": "gpt-5.1", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.1-2025-11-13", + "name": "gpt-5.1-2025-11-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.1-chat-2025-11-13", + "name": "gpt-5.1-chat-2025-11-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.1-codex-2025-11-13", + "name": "gpt-5.1-codex-2025-11-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.1-codex-max-2025-12-04", + "name": "gpt-5.1-codex-max-2025-12-04", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.1-codex-mini-2025-11-13", + "name": "gpt-5.1-codex-mini-2025-11-13", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.2-2025-12-11", + "name": "gpt-5.2-2025-12-11", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.2-chat-2025-12-11", + "name": "gpt-5.2-chat-2025-12-11", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.2-chat-2026-02-10", + "name": "gpt-5.2-chat-2026-02-10", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.2-codex-2026-01-14", + "name": "gpt-5.2-codex-2026-01-14", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.3-chat-2026-03-03", + "name": "gpt-5.3-chat-2026-03-03", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.3-codex-2026-02-20", + "name": "gpt-5.3-codex-2026-02-20", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.3-codex-2026-02-24", + "name": "gpt-5.3-codex-2026-02-24", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.4-2026-03-05", + "name": "gpt-5.4-2026-03-05", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.4-mini-2026-03-17", + "name": "gpt-5.4-mini-2026-03-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.4-nano-2026-03-17", + "name": "gpt-5.4-nano-2026-03-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.05, + "output_per_million": 0.4, + "cache_read_input_per_million": 0.005 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.4-pro-2026-03-05", + "name": "gpt-5.4-pro-2026-03-05", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-5.5-2026-04-24", + "name": "gpt-5.5-2026-04-24", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-audio-1.5-2026-02-23", + "name": "gpt-audio-1.5-2026-02-23", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-audio-2025-08-28", + "name": "gpt-audio-2025-08-28", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-audio-mini-2025-10-06", + "name": "gpt-audio-mini-2025-10-06", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-chat-latest-2026-05-05", + "name": "gpt-chat-latest-2026-05-05", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-image-1", + "name": "gpt-image-1", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "cache_read_input_per_million": 1.25 + } + }, + "images": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 40.0, + "cache_read_input_per_million": 2.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-image-1-2025-04-15", + "name": "gpt-image-1-2025-04-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "cache_read_input_per_million": 1.25 + } + }, + "images": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 40.0, + "cache_read_input_per_million": 2.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-image-1-mini", + "name": "gpt-image-1-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "cache_read_input_per_million": 0.2 + } + }, + "images": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.25 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-image-1-mini-2025-10-06", + "name": "gpt-image-1-mini-2025-10-06", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "cache_read_input_per_million": 0.2 + } + }, + "images": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.25 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-image-1.5", + "name": "gpt-image-1.5", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "cache_read_input_per_million": 1.25 + } + }, + "images": { + "standard": { + "input_per_million": 8.0, + "output_per_million": 32.0, + "cache_read_input_per_million": 2.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-image-1.5-2025-12-16", + "name": "gpt-image-1.5-2025-12-16", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "cache_read_input_per_million": 1.25 + } + }, + "images": { + "standard": { + "input_per_million": 8.0, + "output_per_million": 32.0, + "cache_read_input_per_million": 2.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-oss-120b", + "name": "gpt-oss-120b", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-oss-20b-11", + "name": "gpt-oss-20b-11", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-realtime-1.5-2026-02-23", + "name": "gpt-realtime-1.5-2026-02-23", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-realtime-2025-08-28", + "name": "gpt-realtime-2025-08-28", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-realtime-mini", + "name": "gpt-realtime-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-realtime-mini-2025-10-06", + "name": "gpt-realtime-mini-2025-10-06", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "gpt-realtime-mini-2025-12-15", + "name": "gpt-realtime-mini-2025-12-15", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-3", + "name": "grok-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-3-mini", + "name": "grok-3-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-4-1-fast-non-reasoning", + "name": "grok-4-1-fast-non-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-4-1-fast-reasoning", + "name": "grok-4-1-fast-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-4-20-non-reasoning", + "name": "grok-4-20-non-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-4-20-reasoning", + "name": "grok-4-20-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-4-fast-non-reasoning", + "name": "grok-4-fast-non-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "grok-4-fast-reasoning", + "name": "grok-4-fast-reasoning", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "jais-30b-chat", + "name": "jais-30b-chat", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "jais-30b-chat-2", + "name": "jais-30b-chat-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "jais-30b-chat-3", + "name": "jais-30b-chat-3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "mistral-document-ai-2505", + "name": "mistral-document-ai-2505", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "mistral-document-ai-2512", + "name": "mistral-document-ai-2512", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "mistral-medium-2505", + "name": "mistral-medium-2505", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "mistral-small-2503", + "name": "mistral-small-2503", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "model-router", + "name": "model-router", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "model-router-2025-05-19", + "name": "model-router-2025-05-19", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "model-router-2025-08-07", + "name": "model-router-2025-08-07", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "model-router-2025-11-18", + "name": "model-router-2025-11-18", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o1-2024-12-17", + "name": "o1-2024-12-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 15.0, + "output_per_million": 60.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o1-mini-2024-09-12", + "name": "o1-mini-2024-09-12", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o1-pro", + "name": "o1-pro", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 150.0, + "output_per_million": 600.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o1-pro-2025-03-19", + "name": "o1-pro-2025-03-19", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 150.0, + "output_per_million": 600.0 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o3-deep-research-2025-06-26", + "name": "o3-deep-research-2025-06-26", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o3-deep-research-2025-06-26-ev3", + "name": "o3-deep-research-2025-06-26-ev3", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o3-mini", + "name": "o3-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o3-mini-2025-01-31", + "name": "o3-mini-2025-01-31", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o3-mini-alpha", + "name": "o3-mini-alpha", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o3-mini-alpha-2024-12-17", + "name": "o3-mini-alpha-2024-12-17", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o4-mini", + "name": "o4-mini", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "o4-mini-2025-04-16", + "name": "o4-mini-2025-04-16", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "qwen-3-32b", + "name": "qwen-3-32b", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "qwen3-32b", + "name": "qwen3-32b", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "sora", + "name": "sora", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "sora-2", + "name": "sora-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "sora-2-2025-10-06", + "name": "sora-2-2025-10-06", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "sora-2-2025-12-08", + "name": "sora-2-2025-12-08", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "sora-2025-05-02", + "name": "sora-2025-05-02", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-ada-001", + "name": "text-ada-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-babbage-001", + "name": "text-babbage-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-curie-001", + "name": "text-curie-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-davinci-001", + "name": "text-davinci-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-davinci-002", + "name": "text-davinci-002", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-davinci-003", + "name": "text-davinci-003", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-davinci-fine-tune-002", + "name": "text-davinci-fine-tune-002", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-embedding-3-large", + "name": "text-embedding-3-large", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.13, + "output_per_million": 0.13 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-embedding-3-small", + "name": "text-embedding-3-small", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.02, + "output_per_million": 0.02 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-embedding-ada-002", + "name": "text-embedding-ada-002", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.1 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-embedding-ada-002-2", + "name": "text-embedding-ada-002-2", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.1 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-ada-doc-001", + "name": "text-search-ada-doc-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-ada-query-001", + "name": "text-search-ada-query-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-babbage-doc-001", + "name": "text-search-babbage-doc-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-babbage-query-001", + "name": "text-search-babbage-query-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-curie-doc-001", + "name": "text-search-curie-doc-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-curie-query-001", + "name": "text-search-curie-query-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-davinci-doc-001", + "name": "text-search-davinci-doc-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-search-davinci-query-001", + "name": "text-search-davinci-query-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-similarity-ada-001", + "name": "text-similarity-ada-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-similarity-babbage-001", + "name": "text-similarity-babbage-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-similarity-curie-001", + "name": "text-similarity-curie-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "text-similarity-davinci-001", + "name": "text-similarity-davinci-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "whisper", + "name": "whisper", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.006, + "output_per_million": 0.006 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null + } + }, + { + "id": "whisper-001", + "name": "whisper-001", + "provider": "azure", + "family": null, + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.006, + "output_per_million": 0.006 + } + } + }, + "metadata": { + "object": "model", + "owned_by": null } }, { @@ -1163,7 +9809,7 @@ "name": "Nova 2 Lite", "provider": "bedrock", "family": "nova", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -1206,12 +9852,44 @@ } } }, + { + "id": "amazon.nova-2-sonic-v1:0", + "name": "Nova 2 Sonic", + "provider": "bedrock", + "family": "Nova", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "audio" + ], + "output": [ + "audio", + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-2-sonic-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "amazon.nova-lite-v1:0", "name": "Nova Lite", "provider": "bedrock", "family": "nova-lite", - "created_at": "2024-12-03 00:00:00 +0530", + "created_at": "2024-12-03 00:00:00 UTC", "context_window": 300000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -1234,7 +9912,7 @@ "standard": { "input_per_million": 0.06, "output_per_million": 0.24, - "cached_input_per_million": 0.015 + "cache_read_input_per_million": 0.015 } } }, @@ -1262,7 +9940,7 @@ "name": "Nova Micro", "provider": "bedrock", "family": "nova-micro", - "created_at": "2024-12-03 00:00:00 +0530", + "created_at": "2024-12-03 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -1282,7 +9960,7 @@ "standard": { "input_per_million": 0.035, "output_per_million": 0.14, - "cached_input_per_million": 0.00875 + "cache_read_input_per_million": 0.00875 } } }, @@ -1310,7 +9988,7 @@ "name": "Nova Premier", "provider": "bedrock", "family": "nova", - "created_at": "2024-12-03 00:00:00 +0530", + "created_at": "2024-12-03 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -1355,12 +10033,208 @@ "knowledge": "2024-10" } }, + { + "id": "amazon.nova-premier-v1:0:1000k", + "name": "Nova Premier", + "provider": "bedrock", + "family": "nova", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 12.5 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-premier-v1:0:1000k", + "inference_types": [], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 2.5, + "output": 12.5 + }, + "limit": { + "context": 1000000, + "output": 16384 + }, + "knowledge": "2024-10" + } + }, + { + "id": "amazon.nova-premier-v1:0:20k", + "name": "Nova Premier", + "provider": "bedrock", + "family": "nova", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 20000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 12.5 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-premier-v1:0:20k", + "inference_types": [], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 2.5, + "output": 12.5 + }, + "limit": { + "context": 1000000, + "output": 16384 + }, + "knowledge": "2024-10" + } + }, + { + "id": "amazon.nova-premier-v1:0:8k", + "name": "Nova Premier", + "provider": "bedrock", + "family": "nova", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 8000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 12.5 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-premier-v1:0:8k", + "inference_types": [], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 2.5, + "output": 12.5 + }, + "limit": { + "context": 1000000, + "output": 16384 + }, + "knowledge": "2024-10" + } + }, + { + "id": "amazon.nova-premier-v1:0:mm", + "name": "Nova Premier", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-premier-v1:0:mm", + "inference_types": [], + "converse": {} + } + }, { "id": "amazon.nova-pro-v1:0", "name": "Nova Pro", "provider": "bedrock", "family": "nova-pro", - "created_at": "2024-12-03 00:00:00 +0530", + "created_at": "2024-12-03 00:00:00 UTC", "context_window": 300000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -1383,7 +10257,7 @@ "standard": { "input_per_million": 0.8, "output_per_million": 3.2, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, @@ -1406,15 +10280,259 @@ "knowledge": "2024-10" } }, + { + "id": "amazon.rerank-v1:0", + "name": "Rerank 1.0", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.rerank-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-embed-g1-text-02", + "name": "Titan Text Embeddings v2", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-embed-g1-text-02", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-embed-image-v1", + "name": "Titan Multimodal Embeddings G1", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-embed-image-v1", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-embed-image-v1:0", + "name": "Titan Multimodal Embeddings G1", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-embed-image-v1:0", + "inference_types": [ + "PROVISIONED" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-embed-text-v1", + "name": "Titan Embeddings G1 - Text", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-embed-text-v1", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-embed-text-v1:2:8k", + "name": "Titan Embeddings G1 - Text", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-embed-text-v1:2:8k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-embed-text-v2:0", + "name": "Titan Text Embeddings V2", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-embed-text-v2:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "amazon.titan-image-generator-v2:0", + "name": "Titan Image Generator G1 v2", + "provider": "bedrock", + "family": "amazon", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.titan-image-generator-v2:0", + "inference_types": [ + "PROVISIONED", + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "anthropic.claude-3-5-haiku-20241022-v1:0", "name": "Claude Haiku 3.5", "provider": "bedrock", "family": "claude-haiku", - "created_at": "2024-10-22 00:00:00 +0530", + "created_at": "2024-10-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-07-31", "modalities": { "input": [ "text", @@ -1427,18 +10545,26 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.8, "output_per_million": 4, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08, + "cache_write_input_per_million": 1 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-5-haiku-20241022-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {}, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -1455,7 +10581,7 @@ "context": 200000, "output": 8192 }, - "knowledge": "2024-07" + "knowledge": "2024-07-31" } }, { @@ -1463,10 +10589,10 @@ "name": "Claude Sonnet 3.5", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2024-06-20 00:00:00 +0530", + "created_at": "2024-06-20 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-04-30", "modalities": { "input": [ "text", @@ -1486,7 +10612,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1507,7 +10634,7 @@ "context": 200000, "output": 8192 }, - "knowledge": "2024-04" + "knowledge": "2024-04-30" } }, { @@ -1515,7 +10642,7 @@ "name": "Claude Sonnet 3.5 v2", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2024-10-22 00:00:00 +0530", + "created_at": "2024-10-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -1538,7 +10665,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1567,7 +10695,7 @@ "name": "Claude Sonnet 3.7", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-02-19 00:00:00 +0530", + "created_at": "2025-02-19 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -1590,7 +10718,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1619,7 +10748,7 @@ "name": "Claude Haiku 3", "provider": "bedrock", "family": "claude-haiku", - "created_at": "2024-03-13 00:00:00 +0530", + "created_at": "2024-03-13 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -1635,7 +10764,8 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -1646,6 +10776,12 @@ } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-haiku-20240307-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {}, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -1663,12 +10799,220 @@ "knowledge": "2024-02" } }, + { + "id": "anthropic.claude-3-haiku-20240307-v1:0:200k", + "name": "Claude Haiku 3", + "provider": "bedrock", + "family": "claude-haiku", + "created_at": "2024-03-13 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 1.25 + } + } + }, + "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-haiku-20240307-v1:0:200k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-03-13", + "cost": { + "input": 0.25, + "output": 1.25 + }, + "limit": { + "context": 200000, + "output": 4096 + }, + "knowledge": "2024-02" + } + }, + { + "id": "anthropic.claude-3-haiku-20240307-v1:0:48k", + "name": "Claude Haiku 3", + "provider": "bedrock", + "family": "claude-haiku", + "created_at": "2024-03-13 00:00:00 UTC", + "context_window": 48000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 1.25 + } + } + }, + "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-haiku-20240307-v1:0:48k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-03-13", + "cost": { + "input": 0.25, + "output": 1.25 + }, + "limit": { + "context": 200000, + "output": 4096 + }, + "knowledge": "2024-02" + } + }, + { + "id": "anthropic.claude-3-sonnet-20240229-v1:0", + "name": "Claude 3 Sonnet", + "provider": "bedrock", + "family": "anthropic", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-sonnet-20240229-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "anthropic.claude-3-sonnet-20240229-v1:0:200k", + "name": "Claude 3 Sonnet", + "provider": "bedrock", + "family": "anthropic", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-sonnet-20240229-v1:0:200k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {} + } + }, + { + "id": "anthropic.claude-3-sonnet-20240229-v1:0:28k", + "name": "Claude 3 Sonnet", + "provider": "bedrock", + "family": "anthropic", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-3-sonnet-20240229-v1:0:28k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {} + } + }, { "id": "anthropic.claude-haiku-4-5-20251001-v1:0", "name": "Claude Haiku 4.5", "provider": "bedrock", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -1693,7 +11037,8 @@ "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, @@ -1722,7 +11067,7 @@ "name": "Claude Opus 4.1", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -1746,7 +11091,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -1775,10 +11121,10 @@ "name": "Claude Opus 4", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", @@ -1799,7 +11145,8 @@ "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, @@ -1820,7 +11167,7 @@ "context": 200000, "output": 32000 }, - "knowledge": "2024-04" + "knowledge": "2025-03-31" } }, { @@ -1828,7 +11175,7 @@ "name": "Claude Opus 4.5", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-11-24 00:00:00 +0530", + "created_at": "2025-11-24 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -1853,7 +11200,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -1882,10 +11230,10 @@ "name": "Claude Opus 4.6", "provider": "bedrock", "family": "claude-opus", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", @@ -1907,7 +11255,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -1917,7 +11266,7 @@ "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 5, "output": 25, @@ -1928,7 +11277,62 @@ "context": 1000000, "output": 128000 }, - "knowledge": "2025-05" + "knowledge": "2025-05-31" + } + }, + { + "id": "anthropic.claude-opus-4-7", + "name": "Claude Opus 4.7", + "provider": "bedrock", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" } }, { @@ -1936,10 +11340,10 @@ "name": "Claude Sonnet 4", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", @@ -1960,7 +11364,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -1981,7 +11386,7 @@ "context": 200000, "output": 64000 }, - "knowledge": "2024-04" + "knowledge": "2025-03-31" } }, { @@ -1989,7 +11394,7 @@ "name": "Claude Sonnet 4.5", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -2014,7 +11419,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2043,10 +11449,10 @@ "name": "Claude Sonnet 4.6", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", @@ -2067,7 +11473,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2077,7 +11484,7 @@ "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 3, "output": 15, @@ -2088,15 +11495,337 @@ "context": 1000000, "output": 64000 }, + "knowledge": "2025-08-31" + } + }, + { + "id": "au.anthropic.claude-opus-4-6-v1", + "name": "AU Anthropic Claude Opus 4.6", + "provider": "bedrock", + "family": "claude-opus", + "created_at": "2026-02-05 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 16.5, + "output_per_million": 82.5, + "cache_read_input_per_million": 1.65, + "cache_write_input_per_million": 20.625 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-02-05", + "cost": { + "input": 16.5, + "output": 82.5, + "cache_read": 1.65, + "cache_write": 20.625 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2025-05" + } + }, + { + "id": "au.anthropic.claude-sonnet-4-6", + "name": "AU Anthropic Claude Sonnet 4.6", + "provider": "bedrock", + "family": "claude-sonnet", + "created_at": "2026-02-17 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.3, + "output_per_million": 16.5, + "cache_read_input_per_million": 0.33, + "cache_write_input_per_million": 4.125 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-02-17", + "cost": { + "input": 3.3, + "output": 16.5, + "cache_read": 0.33, + "cache_write": 4.125 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, "knowledge": "2025-08" } }, + { + "id": "cohere.command-r-plus-v1:0", + "name": "Command R+", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.command-r-plus-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "cohere.command-r-v1:0", + "name": "Command R", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.command-r-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "cohere.embed-english-v3", + "name": "Embed English", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.embed-english-v3", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "cohere.embed-english-v3:0:512", + "name": "Embed English", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.embed-english-v3:0:512", + "inference_types": [ + "PROVISIONED" + ], + "converse": {} + } + }, + { + "id": "cohere.embed-multilingual-v3", + "name": "Embed Multilingual", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.embed-multilingual-v3", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "cohere.embed-multilingual-v3:0:512", + "name": "Embed Multilingual", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.embed-multilingual-v3:0:512", + "inference_types": [ + "PROVISIONED" + ], + "converse": {} + } + }, + { + "id": "cohere.rerank-v3-5:0", + "name": "Rerank 3.5", + "provider": "bedrock", + "family": "cohere", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.rerank-v3-5:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "deepseek.r1-v1:0", "name": "DeepSeek-R1", "provider": "bedrock", "family": "deepseek-thinking", - "created_at": "2025-01-20 00:00:00 +0530", + "created_at": "2025-01-20 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -2143,7 +11872,7 @@ "name": "DeepSeek-V3.1", "provider": "bedrock", "family": "deepseek", - "created_at": "2025-09-18 00:00:00 +0530", + "created_at": "2025-09-18 00:00:00 UTC", "context_window": 163840, "max_output_tokens": 81920, "knowledge_cutoff": null, @@ -2158,7 +11887,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -2169,6 +11899,24 @@ } }, "metadata": { + "provider_name": "DeepSeek", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/deepseek.v3-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 163840, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -2191,7 +11939,7 @@ "name": "DeepSeek-V3.2", "provider": "bedrock", "family": "deepseek", - "created_at": "2026-02-06 00:00:00 +0530", + "created_at": "2026-02-06 00:00:00 UTC", "context_window": 163840, "max_output_tokens": 81920, "knowledge_cutoff": null, @@ -2205,7 +11953,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -2216,6 +11965,24 @@ } }, "metadata": { + "provider_name": "DeepSeek", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/deepseek.v3.2", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 163840, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -2238,7 +12005,7 @@ "name": "Claude Haiku 4.5 (EU)", "provider": "bedrock", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -2263,7 +12030,8 @@ "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, @@ -2292,7 +12060,7 @@ "name": "Claude Opus 4.5 (EU)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-11-24 00:00:00 +0530", + "created_at": "2025-11-24 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -2317,7 +12085,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -2346,10 +12115,10 @@ "name": "Claude Opus 4.6 (EU)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", @@ -2371,7 +12140,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -2381,7 +12151,7 @@ "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 5, "output": 25, @@ -2392,7 +12162,62 @@ "context": 1000000, "output": 128000 }, - "knowledge": "2025-05" + "knowledge": "2025-05-31" + } + }, + { + "id": "eu.anthropic.claude-opus-4-7", + "name": "Claude Opus 4.7 (EU)", + "provider": "bedrock", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" } }, { @@ -2400,10 +12225,10 @@ "name": "Claude Sonnet 4 (EU)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", @@ -2424,7 +12249,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2445,7 +12271,7 @@ "context": 200000, "output": 64000 }, - "knowledge": "2024-04" + "knowledge": "2025-03-31" } }, { @@ -2453,7 +12279,7 @@ "name": "Claude Sonnet 4.5 (EU)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -2478,7 +12304,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2507,10 +12334,10 @@ "name": "Claude Sonnet 4.6 (EU)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", @@ -2531,7 +12358,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2541,7 +12369,7 @@ "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 3, "output": 15, @@ -2552,7 +12380,7 @@ "context": 1000000, "output": 64000 }, - "knowledge": "2025-08" + "knowledge": "2025-08-31" } }, { @@ -2560,7 +12388,7 @@ "name": "Claude Haiku 4.5 (Global)", "provider": "bedrock", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -2585,7 +12413,8 @@ "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, @@ -2614,7 +12443,7 @@ "name": "Claude Opus 4.5 (Global)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-11-24 00:00:00 +0530", + "created_at": "2025-11-24 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -2639,7 +12468,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -2668,10 +12498,10 @@ "name": "Claude Opus 4.6 (Global)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", @@ -2693,7 +12523,8 @@ "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, @@ -2703,7 +12534,7 @@ "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 5, "output": 25, @@ -2714,7 +12545,62 @@ "context": 1000000, "output": 128000 }, - "knowledge": "2025-05" + "knowledge": "2025-05-31" + } + }, + { + "id": "global.anthropic.claude-opus-4-7", + "name": "Claude Opus 4.7 (Global)", + "provider": "bedrock", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" } }, { @@ -2722,10 +12608,10 @@ "name": "Claude Sonnet 4 (Global)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", @@ -2746,7 +12632,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2767,7 +12654,7 @@ "context": 200000, "output": 64000 }, - "knowledge": "2024-04" + "knowledge": "2025-03-31" } }, { @@ -2775,7 +12662,7 @@ "name": "Claude Sonnet 4.5 (Global)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -2800,7 +12687,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2829,10 +12717,10 @@ "name": "Claude Sonnet 4.6 (Global)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", @@ -2853,7 +12741,8 @@ "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, @@ -2863,7 +12752,7 @@ "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 3, "output": 15, @@ -2874,7 +12763,7 @@ "context": 1000000, "output": 64000 }, - "knowledge": "2025-08" + "knowledge": "2025-08-31" } }, { @@ -2882,7 +12771,7 @@ "name": "Google Gemma 3 12B", "provider": "bedrock", "family": "gemma", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -2897,7 +12786,9 @@ }, "capabilities": [ "structured_output", - "vision" + "vision", + "streaming", + "function_calling" ], "pricing": { "text_tokens": { @@ -2908,6 +12799,27 @@ } }, "metadata": { + "provider_name": "Google", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/google.gemma-3-12b-it", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -2930,7 +12842,7 @@ "name": "Google Gemma 3 27B Instruct", "provider": "bedrock", "family": "gemma", - "created_at": "2025-07-27 00:00:00 +0530", + "created_at": "2025-07-27 00:00:00 UTC", "context_window": 202752, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -2946,7 +12858,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -2957,6 +12870,27 @@ } }, "metadata": { + "provider_name": "Google", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/google.gemma-3-27b-it", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -2979,7 +12913,7 @@ "name": "Gemma 3 4B IT", "provider": "bedrock", "family": "gemma", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -2994,7 +12928,8 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -3005,6 +12940,27 @@ } }, "metadata": { + "provider_name": "Google", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/google.gemma-3-4b-it", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -3021,12 +12977,42 @@ } } }, + { + "id": "luma.ray-v2:0", + "name": "Ray v2", + "provider": "bedrock", + "family": "luma ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "video" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Luma AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/luma.ray-v2:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "meta.llama3-1-405b-instruct-v1:0", "name": "Llama 3.1 405B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-07-23 00:00:00 +0530", + "created_at": "2024-07-23 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3039,7 +13025,8 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming" ], "pricing": { "text_tokens": { @@ -3050,6 +13037,12 @@ } }, "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-1-405b-instruct-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {}, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3072,7 +13065,7 @@ "name": "Llama 3.1 70B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-07-23 00:00:00 +0530", + "created_at": "2024-07-23 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3085,7 +13078,8 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming" ], "pricing": { "text_tokens": { @@ -3096,6 +13090,66 @@ } }, "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-1-70b-instruct-v1:0", + "inference_types": [ + "ON_DEMAND", + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-07-23", + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "meta.llama3-1-70b-instruct-v1:0:128k", + "name": "Llama 3.1 70B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-07-23 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.72, + "output_per_million": 0.72 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-1-70b-instruct-v1:0:128k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3118,7 +13172,7 @@ "name": "Llama 3.1 8B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-07-23 00:00:00 +0530", + "created_at": "2024-07-23 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3131,7 +13185,8 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming" ], "pricing": { "text_tokens": { @@ -3142,6 +13197,66 @@ } }, "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-1-8b-instruct-v1:0", + "inference_types": [ + "ON_DEMAND", + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-07-23", + "cost": { + "input": 0.22, + "output": 0.22 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "meta.llama3-1-8b-instruct-v1:0:128k", + "name": "Llama 3.1 8B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-07-23 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.22, + "output_per_million": 0.22 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-1-8b-instruct-v1:0:128k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3164,7 +13279,7 @@ "name": "Llama 3.2 11B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-09-25 00:00:00 +0530", + "created_at": "2024-09-25 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3207,12 +13322,67 @@ "knowledge": "2023-12" } }, + { + "id": "meta.llama3-2-11b-instruct-v1:0:128k", + "name": "Llama 3.2 11B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.16, + "output_per_million": 0.16 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-11b-instruct-v1:0:128k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.16, + "output": 0.16 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, { "id": "meta.llama3-2-1b-instruct-v1:0", "name": "Llama 3.2 1B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-09-25 00:00:00 +0530", + "created_at": "2024-09-25 00:00:00 UTC", "context_window": 131000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3253,12 +13423,65 @@ "knowledge": "2023-12" } }, + { + "id": "meta.llama3-2-1b-instruct-v1:0:128k", + "name": "Llama 3.2 1B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.1 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-1b-instruct-v1:0:128k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 131000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, { "id": "meta.llama3-2-3b-instruct-v1:0", "name": "Llama 3.2 3B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-09-25 00:00:00 +0530", + "created_at": "2024-09-25 00:00:00 UTC", "context_window": 131000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3299,12 +13522,65 @@ "knowledge": "2023-12" } }, + { + "id": "meta.llama3-2-3b-instruct-v1:0:128k", + "name": "Llama 3.2 3B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.15 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-3b-instruct-v1:0:128k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 131000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, { "id": "meta.llama3-2-90b-instruct-v1:0", "name": "Llama 3.2 90B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-09-25 00:00:00 +0530", + "created_at": "2024-09-25 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3347,12 +13623,67 @@ "knowledge": "2023-12" } }, + { + "id": "meta.llama3-2-90b-instruct-v1:0:128k", + "name": "Llama 3.2 90B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.72, + "output_per_million": 0.72 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-90b-instruct-v1:0:128k", + "inference_types": [ + "PROVISIONED" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, { "id": "meta.llama3-3-70b-instruct-v1:0", "name": "Llama 3.3 70B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2024-12-06 00:00:00 +0530", + "created_at": "2024-12-06 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3393,12 +13724,125 @@ "knowledge": "2023-12" } }, + { + "id": "meta.llama3-3-70b-instruct-v1:0:128k", + "name": "Llama 3.3 70B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-12-06 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.72, + "output_per_million": 0.72 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-3-70b-instruct-v1:0:128k", + "inference_types": [], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-12-06", + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "meta.llama3-70b-instruct-v1:0", + "name": "Llama 3 70B Instruct", + "provider": "bedrock", + "family": "meta", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-70b-instruct-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "meta.llama3-8b-instruct-v1:0", + "name": "Llama 3 8B Instruct", + "provider": "bedrock", + "family": "meta", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-8b-instruct-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "meta.llama4-maverick-17b-instruct-v1:0", "name": "Llama 4 Maverick 17B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2025-04-05 00:00:00 +0530", + "created_at": "2025-04-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -3446,7 +13890,7 @@ "name": "Llama 4 Scout 17B Instruct", "provider": "bedrock", "family": "llama", - "created_at": "2025-04-05 00:00:00 +0530", + "created_at": "2025-04-05 00:00:00 UTC", "context_window": 3500000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -3494,7 +13938,7 @@ "name": "MiniMax M2", "provider": "bedrock", "family": "minimax", - "created_at": "2025-10-27 00:00:00 +0530", + "created_at": "2025-10-27 00:00:00 UTC", "context_window": 204608, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -3508,7 +13952,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -3519,6 +13964,24 @@ } }, "metadata": { + "provider_name": "MiniMax", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/minimax.minimax-m2", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 409600, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3540,7 +14003,7 @@ "name": "MiniMax M2.1", "provider": "bedrock", "family": "minimax", - "created_at": "2025-12-23 00:00:00 +0530", + "created_at": "2025-12-23 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -3554,7 +14017,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -3565,6 +14029,24 @@ } }, "metadata": { + "provider_name": "MiniMax", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/minimax.minimax-m2.1", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 196608, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3586,7 +14068,7 @@ "name": "MiniMax M2.5", "provider": "bedrock", "family": "minimax", - "created_at": "2026-03-18 00:00:00 +0530", + "created_at": "2026-03-18 00:00:00 UTC", "context_window": 196608, "max_output_tokens": 98304, "knowledge_cutoff": null, @@ -3600,7 +14082,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -3611,6 +14094,24 @@ } }, "metadata": { + "provider_name": "MiniMax", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/minimax.minimax-m2.5", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 196608, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3632,7 +14133,7 @@ "name": "Devstral 2 123B", "provider": "bedrock", "family": "devstral", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -3645,7 +14146,8 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming" ], "pricing": { "text_tokens": { @@ -3656,6 +14158,22 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.devstral-2-123b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3677,7 +14195,7 @@ "name": "Magistral Small 1.2", "provider": "bedrock", "family": "magistral", - "created_at": "2025-12-02 00:00:00 +0530", + "created_at": "2025-12-02 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 40000, "knowledge_cutoff": null, @@ -3694,7 +14212,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -3705,6 +14224,29 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.magistral-small-2509", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3726,7 +14268,7 @@ "name": "Ministral 14B 3.0", "provider": "bedrock", "family": "ministral", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3740,7 +14282,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -3751,6 +14294,27 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.ministral-3-14b-instruct", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -3772,7 +14336,7 @@ "name": "Ministral 3 3B", "provider": "bedrock", "family": "ministral", - "created_at": "2025-12-02 00:00:00 +0530", + "created_at": "2025-12-02 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -3788,7 +14352,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -3799,6 +14364,27 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.ministral-3-3b-instruct", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3820,7 +14406,7 @@ "name": "Ministral 3 8B", "provider": "bedrock", "family": "ministral", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3834,7 +14420,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -3845,6 +14432,27 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.ministral-3-8b-instruct", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -3861,12 +14469,105 @@ } } }, + { + "id": "mistral.mistral-7b-instruct-v0:2", + "name": "Mistral 7B Instruct", + "provider": "bedrock", + "family": "mistral ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.mistral-7b-instruct-v0:2", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "mistral.mistral-large-2402-v1:0", + "name": "Mistral Large (24.02)", + "provider": "bedrock", + "family": "mistral ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.mistral-large-2402-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "mistral.mistral-large-2407-v1:0", + "name": "Mistral Large (24.07)", + "provider": "bedrock", + "family": "mistral ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.mistral-large-2407-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "mistral.mistral-large-3-675b-instruct", "name": "Mistral Large 3", "provider": "bedrock", "family": "mistral", - "created_at": "2025-12-02 00:00:00 +0530", + "created_at": "2025-12-02 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -3882,7 +14583,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -3893,6 +14595,27 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.mistral-large-3-675b-instruct", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -3909,12 +14632,43 @@ } } }, + { + "id": "mistral.mixtral-8x7b-instruct-v0:1", + "name": "Mixtral 8x7B Instruct", + "provider": "bedrock", + "family": "mistral ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.mixtral-8x7b-instruct-v0:1", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, { "id": "mistral.pixtral-large-2502-v1:0", "name": "Pixtral Large (25.02)", "provider": "bedrock", "family": "mistral", - "created_at": "2025-04-08 00:00:00 +0530", + "created_at": "2025-04-08 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -3961,7 +14715,7 @@ "name": "Voxtral Mini 3B 2507", "provider": "bedrock", "family": "mistral", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -3976,7 +14730,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -3987,6 +14742,22 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.voxtral-mini-3b-2507", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 32768, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4008,7 +14779,7 @@ "name": "Voxtral Small 24B 2507", "provider": "bedrock", "family": "mistral", - "created_at": "2025-07-01 00:00:00 +0530", + "created_at": "2025-07-01 00:00:00 UTC", "context_window": 32000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -4023,7 +14794,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4034,6 +14806,22 @@ } }, "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.voxtral-small-24b-2507", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 32768, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4055,7 +14843,7 @@ "name": "Kimi K2 Thinking", "provider": "bedrock", "family": "kimi-thinking", - "created_at": "2025-12-02 00:00:00 +0530", + "created_at": "2025-12-02 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -4070,7 +14858,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -4081,6 +14870,24 @@ } }, "metadata": { + "provider_name": "Moonshot AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/moonshot.kimi-k2-thinking", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4103,7 +14910,7 @@ "name": "Kimi K2.5", "provider": "bedrock", "family": "kimi", - "created_at": "2026-02-06 00:00:00 +0530", + "created_at": "2026-02-06 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -4119,7 +14926,8 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -4130,6 +14938,29 @@ } }, "metadata": { + "provider_name": "Moonshot AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/moonshotai.kimi-k2.5", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4152,7 +14983,7 @@ "name": "NVIDIA Nemotron Nano 12B v2 VL BF16", "provider": "bedrock", "family": "nemotron", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4168,7 +14999,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -4179,6 +15011,27 @@ } }, "metadata": { + "provider_name": "NVIDIA", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/nvidia.nemotron-nano-12b-v2", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4200,7 +15053,7 @@ "name": "NVIDIA Nemotron Nano 3 30B", "provider": "bedrock", "family": "nemotron", - "created_at": "2025-12-23 00:00:00 +0530", + "created_at": "2025-12-23 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4214,7 +15067,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -4225,6 +15079,24 @@ } }, "metadata": { + "provider_name": "NVIDIA", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/nvidia.nemotron-nano-3-30b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4246,7 +15118,7 @@ "name": "NVIDIA Nemotron Nano 9B v2", "provider": "bedrock", "family": "nemotron", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4260,7 +15132,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4271,6 +15144,22 @@ } }, "metadata": { + "provider_name": "NVIDIA", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/nvidia.nemotron-nano-9b-v2", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4292,7 +15181,7 @@ "name": "NVIDIA Nemotron 3 Super 120B A12B", "provider": "bedrock", "family": "nemotron", - "created_at": "2026-03-11 00:00:00 +0530", + "created_at": "2026-03-11 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -4306,7 +15195,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -4317,6 +15207,22 @@ } }, "metadata": { + "provider_name": "NVIDIA", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/nvidia.nemotron-super-3-120b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4338,7 +15244,7 @@ "name": "gpt-oss-120b", "provider": "bedrock", "family": "gpt-oss", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4352,7 +15258,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4363,6 +15270,24 @@ } }, "metadata": { + "provider_name": "OpenAI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/openai.gpt-oss-120b-1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": null, + "maxTokensDefault": 4096, + "maxTokensMaximum": 128000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4384,7 +15309,7 @@ "name": "gpt-oss-20b", "provider": "bedrock", "family": "gpt-oss", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4398,7 +15323,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4409,6 +15335,24 @@ } }, "metadata": { + "provider_name": "OpenAI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/openai.gpt-oss-20b-1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": null, + "maxTokensDefault": 4096, + "maxTokensMaximum": 128000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4430,7 +15374,7 @@ "name": "GPT OSS Safeguard 120B", "provider": "bedrock", "family": "gpt-oss", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4444,7 +15388,9 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming", + "reasoning" ], "pricing": { "text_tokens": { @@ -4455,6 +15401,24 @@ } }, "metadata": { + "provider_name": "OpenAI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/openai.gpt-oss-safeguard-120b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4476,7 +15440,7 @@ "name": "GPT OSS Safeguard 20B", "provider": "bedrock", "family": "gpt-oss", - "created_at": "2024-12-01 00:00:00 +0530", + "created_at": "2024-12-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -4490,7 +15454,9 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming", + "reasoning" ], "pricing": { "text_tokens": { @@ -4501,6 +15467,24 @@ } }, "metadata": { + "provider_name": "OpenAI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/openai.gpt-oss-safeguard-20b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4522,7 +15506,7 @@ "name": "Qwen3 235B A22B 2507", "provider": "bedrock", "family": "qwen", - "created_at": "2025-09-18 00:00:00 +0530", + "created_at": "2025-09-18 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -4536,7 +15520,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4547,6 +15532,22 @@ } }, "metadata": { + "provider_name": "Qwen", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/qwen.qwen3-235b-a22b-2507-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4569,7 +15570,7 @@ "name": "Qwen3 32B (dense)", "provider": "bedrock", "family": "qwen", - "created_at": "2025-09-18 00:00:00 +0530", + "created_at": "2025-09-18 00:00:00 UTC", "context_window": 16384, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -4584,7 +15585,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -4595,6 +15597,24 @@ } }, "metadata": { + "provider_name": "Qwen", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/qwen.qwen3-32b-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":true}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 32768, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4617,7 +15637,7 @@ "name": "Qwen3 Coder 30B A3B Instruct", "provider": "bedrock", "family": "qwen", - "created_at": "2025-09-18 00:00:00 +0530", + "created_at": "2025-09-18 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -4631,7 +15651,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4642,6 +15663,22 @@ } }, "metadata": { + "provider_name": "Qwen", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/qwen.qwen3-coder-30b-a3b-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4664,7 +15701,7 @@ "name": "Qwen3 Coder 480B A35B Instruct", "provider": "bedrock", "family": "qwen", - "created_at": "2025-09-18 00:00:00 +0530", + "created_at": "2025-09-18 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -4678,7 +15715,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4689,6 +15727,22 @@ } }, "metadata": { + "provider_name": "Qwen", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/qwen.qwen3-coder-480b-a35b-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "", + "maxTokensDefault": null, + "maxTokensMaximum": 131072, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -4711,7 +15765,7 @@ "name": "Qwen3 Coder Next", "provider": "bedrock", "family": "qwen", - "created_at": "2026-02-06 00:00:00 +0530", + "created_at": "2026-02-06 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -4758,7 +15812,7 @@ "name": "Qwen/Qwen3-Next-80B-A3B-Instruct", "provider": "bedrock", "family": "qwen", - "created_at": "2025-09-18 00:00:00 +0530", + "created_at": "2025-09-18 00:00:00 UTC", "context_window": 262000, "max_output_tokens": 262000, "knowledge_cutoff": null, @@ -4772,7 +15826,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -4783,6 +15838,24 @@ } }, "metadata": { + "provider_name": "Qwen", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/qwen.qwen3-next-80b-a3b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4804,7 +15877,7 @@ "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", "provider": "bedrock", "family": "qwen", - "created_at": "2025-10-04 00:00:00 +0530", + "created_at": "2025-10-04 00:00:00 UTC", "context_window": 262000, "max_output_tokens": 262000, "knowledge_cutoff": null, @@ -4820,7 +15893,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -4831,6 +15905,29 @@ } }, "metadata": { + "provider_name": "Qwen", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/qwen.qwen3-vl-235b-a22b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 262144, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "png", + "jpeg", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4847,12 +15944,444 @@ } } }, + { + "id": "stability.sd3-5-large-v1:0", + "name": "Stable Diffusion 3.5 Large", + "provider": "bedrock", + "family": "stability ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.sd3-5-large-v1:0", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "stability.stable-image-core-v1:1", + "name": "Stable Image Core 1.0", + "provider": "bedrock", + "family": "stability ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-core-v1:1", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "stability.stable-image-ultra-v1:1", + "name": "Stable Image Ultra 1.0", + "provider": "bedrock", + "family": "stability ai", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-ultra-v1:1", + "inference_types": [ + "ON_DEMAND" + ], + "converse": {} + } + }, + { + "id": "us.amazon.nova-2-lite-v1:0", + "name": "Nova 2 Lite", + "provider": "bedrock", + "family": "nova", + "created_at": "2024-12-01 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.33, + "output_per_million": 2.75 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-2-lite-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"topK\":{\"type\":\"number\",\"default\":50,\"minimum\":1,\"maximum\":100},\"reasoningConfig\":{\"budgetTokens\":{\"type\":\"enum\",\"default\":\"low\",\"minimum\":10000,\"maximum\":64000,\"enum\":{\"low\":10000,\"medium\":40000,\"high\":64000},\"smartSyncEnabled\":true}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 65535, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf", + "docx" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [ + "mkv", + "mov", + "mp4", + "webm", + "flv", + "mpeg", + "mpg", + "wmv", + "three_gp" + ] + }, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2024-12-01", + "cost": { + "input": 0.33, + "output": 2.75 + }, + "limit": { + "context": 128000, + "output": 4096 + } + } + }, + { + "id": "us.amazon.nova-lite-v1:0", + "name": "Nova Lite", + "provider": "bedrock", + "family": "nova-lite", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 300000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.06, + "output_per_million": 0.24, + "cache_read_input_per_million": 0.015 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-lite-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 0.06, + "output": 0.24, + "cache_read": 0.015 + }, + "limit": { + "context": 300000, + "output": 8192 + }, + "knowledge": "2024-10" + } + }, + { + "id": "us.amazon.nova-micro-v1:0", + "name": "Nova Micro", + "provider": "bedrock", + "family": "nova-micro", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.035, + "output_per_million": 0.14, + "cache_read_input_per_million": 0.00875 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-micro-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 0.035, + "output": 0.14, + "cache_read": 0.00875 + }, + "limit": { + "context": 128000, + "output": 8192 + }, + "knowledge": "2024-10" + } + }, + { + "id": "us.amazon.nova-premier-v1:0", + "name": "Nova Premier", + "provider": "bedrock", + "family": "nova", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 12.5 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-premier-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 2.5, + "output": 12.5 + }, + "limit": { + "context": 1000000, + "output": 16384 + }, + "knowledge": "2024-10" + } + }, + { + "id": "us.amazon.nova-pro-v1:0", + "name": "Nova Pro", + "provider": "bedrock", + "family": "nova-pro", + "created_at": "2024-12-03 00:00:00 UTC", + "context_window": 300000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.8, + "output_per_million": 3.2, + "cache_read_input_per_million": 0.2 + } + } + }, + "metadata": { + "provider_name": "Amazon", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/amazon.nova-pro-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": null, + "maxTokensDefault": null, + "maxTokensMaximum": 10000, + "reasoningSupported": null, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf", + "docx" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [ + "mkv", + "mov", + "mp4", + "webm", + "flv", + "mpeg", + "mpg", + "wmv", + "three_gp" + ] + }, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-12-03", + "cost": { + "input": 0.8, + "output": 3.2, + "cache_read": 0.2 + }, + "limit": { + "context": 300000, + "output": 8192 + }, + "knowledge": "2024-10" + } + }, { "id": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "name": "Claude Haiku 4.5 (US)", "provider": "bedrock", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -4870,18 +16399,45 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-haiku-4-5-20251001-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"top_k\":{\"type\":\"number\",\"default\":250,\"minimum\":0,\"maximum\":500},\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"integer\",\"default\":2048,\"minimum\":1024,\"maximum\":63999}}}", + "maxTokensDefault": 64000, + "maxTokensMaximum": 64000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4906,7 +16462,7 @@ "name": "Claude Opus 4.1 (US)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -4923,18 +16479,45 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-opus-4-1-20250805-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"topK\":{\"type\":\"number\",\"default\":250,\"minimum\":0,\"maximum\":500},\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"integer\",\"default\":2048,\"minimum\":1024,\"maximum\":63999}}}", + "maxTokensDefault": 1024, + "maxTokensMaximum": 32000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -4959,10 +16542,10 @@ "name": "Claude Opus 4 (US)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", @@ -4976,18 +16559,26 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-opus-4-20250514-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -5004,7 +16595,7 @@ "context": 200000, "output": 32000 }, - "knowledge": "2024-04" + "knowledge": "2025-03-31" } }, { @@ -5012,7 +16603,7 @@ "name": "Claude Opus 4.5 (US)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2025-11-24 00:00:00 +0530", + "created_at": "2025-11-24 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -5030,18 +16621,45 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-opus-4-5-20251101-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"top_k\":{\"type\":\"number\",\"default\":250,\"minimum\":0,\"maximum\":500},\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"integer\",\"default\":2048,\"minimum\":1024,\"maximum\":63999}}}", + "maxTokensDefault": 64000, + "maxTokensMaximum": 64000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -5066,10 +16684,10 @@ "name": "Claude Opus 4.6 (US)", "provider": "bedrock", "family": "claude-opus", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", @@ -5084,24 +16702,51 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-opus-4-6-v1", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"top_k\":{\"type\":\"number\",\"default\":250,\"minimum\":0,\"maximum\":500},\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"enum\",\"default\":\"low\",\"enum\":{\"low\":1024,\"medium\":40000,\"high\":63999},\"minimum\":1024,\"maximum\":63999}}}", + "maxTokensDefault": 128000, + "maxTokensMaximum": 128000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 5, "output": 25, @@ -5112,7 +16757,88 @@ "context": 1000000, "output": 128000 }, - "knowledge": "2025-05" + "knowledge": "2025-05-31" + } + }, + { + "id": "us.anthropic.claude-opus-4-7", + "name": "Claude Opus 4.7 (US)", + "provider": "bedrock", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-opus-4-7", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"enum\",\"default\":\"low\",\"enum\":{\"low\":1024,\"medium\":40000,\"high\":63999},\"minimum\":1024,\"maximum\":63999}},\"hideSamplingParameter\":true}", + "maxTokensDefault": 4096, + "maxTokensMaximum": 128000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" } }, { @@ -5120,10 +16846,10 @@ "name": "Claude Sonnet 4 (US)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-03-31", "modalities": { "input": [ "text", @@ -5137,18 +16863,45 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-sonnet-4-20250514-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": null, + "maxTokensDefault": 8192, + "maxTokensMaximum": 65536, + "reasoningSupported": { + "embedded": true + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -5165,7 +16918,7 @@ "context": 200000, "output": 64000 }, - "knowledge": "2024-04" + "knowledge": "2025-03-31" } }, { @@ -5173,7 +16926,7 @@ "name": "Claude Sonnet 4.5 (US)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -5191,18 +16944,45 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-sonnet-4-5-20250929-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"top_k\":{\"type\":\"number\",\"default\":250,\"minimum\":0,\"maximum\":500},\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"integer\",\"default\":2048,\"minimum\":1024,\"maximum\":63999}}}", + "maxTokensDefault": 64000, + "maxTokensMaximum": 64000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": null, + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, @@ -5227,10 +17007,10 @@ "name": "Claude Sonnet 4.6 (US)", "provider": "bedrock", "family": "claude-sonnet", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", @@ -5244,24 +17024,52 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { + "provider_name": "Anthropic", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-sonnet-4-6", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"top_k\":{\"type\":\"number\",\"default\":250,\"minimum\":0,\"maximum\":500},\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false},\"budgetTokens\":{\"type\":\"enum\",\"default\":\"low\",\"enum\":{\"low\":1024,\"medium\":40000,\"high\":63999},\"minimum\":1024,\"maximum\":63999}}}", + "maxTokensDefault": 128000, + "maxTokensMaximum": 128000, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [ + "pdf" + ], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": false, "attachment": true, "temperature": true, - "last_updated": "2026-03-18", + "last_updated": "2026-03-13", "cost": { "input": 3, "output": 15, @@ -5272,7 +17080,1113 @@ "context": 1000000, "output": 64000 }, - "knowledge": "2025-08" + "knowledge": "2025-08-31" + } + }, + { + "id": "us.cohere.embed-v4:0", + "name": "Embed v4", + "provider": "bedrock", + "family": "Embed", + "created_at": null, + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Cohere", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/cohere.embed-v4:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.deepseek.r1-v1:0", + "name": "DeepSeek-R1", + "provider": "bedrock", + "family": "deepseek-thinking", + "created_at": "2025-01-20 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.35, + "output_per_million": 5.4 + } + } + }, + "metadata": { + "provider_name": "DeepSeek", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/deepseek.r1-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2025-05-29", + "cost": { + "input": 1.35, + "output": 5.4 + }, + "limit": { + "context": 128000, + "output": 32768 + }, + "knowledge": "2024-07" + } + }, + { + "id": "us.meta.llama3-2-11b-instruct-v1:0", + "name": "Llama 3.2 11B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.16, + "output_per_million": 0.16 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-11b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.16, + "output": 0.16 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "us.meta.llama3-2-1b-instruct-v1:0", + "name": "Llama 3.2 1B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 131000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.1 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-1b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.1, + "output": 0.1 + }, + "limit": { + "context": 131000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "us.meta.llama3-2-3b-instruct-v1:0", + "name": "Llama 3.2 3B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 131000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.15 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-3b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.15, + "output": 0.15 + }, + "limit": { + "context": 131000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "us.meta.llama3-2-90b-instruct-v1:0", + "name": "Llama 3.2 90B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.72, + "output_per_million": 0.72 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-2-90b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2024-09-25", + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "us.meta.llama3-3-70b-instruct-v1:0", + "name": "Llama 3.3 70B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2024-12-06 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.72, + "output_per_million": 0.72 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama3-3-70b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2024-12-06", + "cost": { + "input": 0.72, + "output": 0.72 + }, + "limit": { + "context": 128000, + "output": 4096 + }, + "knowledge": "2023-12" + } + }, + { + "id": "us.meta.llama4-maverick-17b-instruct-v1:0", + "name": "Llama 4 Maverick 17B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2025-04-05 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.24, + "output_per_million": 0.97 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama4-maverick-17b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2025-04-05", + "cost": { + "input": 0.24, + "output": 0.97 + }, + "limit": { + "context": 1000000, + "output": 16384 + }, + "knowledge": "2024-08" + } + }, + { + "id": "us.meta.llama4-scout-17b-instruct-v1:0", + "name": "Llama 4 Scout 17B Instruct", + "provider": "bedrock", + "family": "llama", + "created_at": "2025-04-05 00:00:00 UTC", + "context_window": 3500000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.17, + "output_per_million": 0.66 + } + } + }, + "metadata": { + "provider_name": "Meta", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/meta.llama4-scout-17b-instruct-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2025-04-05", + "cost": { + "input": 0.17, + "output": 0.66 + }, + "limit": { + "context": 3500000, + "output": 16384 + }, + "knowledge": "2024-08" + } + }, + { + "id": "us.mistral.pixtral-large-2502-v1:0", + "name": "Pixtral Large (25.02)", + "provider": "bedrock", + "family": "mistral", + "created_at": "2025-04-08 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2, + "output_per_million": 6 + } + } + }, + "metadata": { + "provider_name": "Mistral AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/mistral.pixtral-large-2502-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2025-04-08", + "cost": { + "input": 2, + "output": 6 + }, + "limit": { + "context": 128000, + "output": 8192 + } + } + }, + { + "id": "us.stability.stable-conservative-upscale-v1:0", + "name": "Stable Image Conservative Upscale", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-conservative-upscale-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-creative-upscale-v1:0", + "name": "Stable Image Creative Upscale", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-creative-upscale-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-fast-upscale-v1:0", + "name": "Stable Image Fast Upscale", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-fast-upscale-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-control-sketch-v1:0", + "name": "Stable Image Control Sketch", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-control-sketch-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-control-structure-v1:0", + "name": "Stable Image Control Structure", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-control-structure-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-erase-object-v1:0", + "name": "Stable Image Erase Object", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-erase-object-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-inpaint-v1:0", + "name": "Stable Image Inpaint", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-inpaint-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-remove-background-v1:0", + "name": "Stable Image Remove Background", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-remove-background-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-search-recolor-v1:0", + "name": "Stable Image Search and Recolor", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-search-recolor-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-search-replace-v1:0", + "name": "Stable Image Search and Replace", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-search-replace-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-image-style-guide-v1:0", + "name": "Stable Image Style Guide", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-image-style-guide-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-outpaint-v1:0", + "name": "Stable Image Outpaint", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-outpaint-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.stability.stable-style-transfer-v1:0", + "name": "Stable Image Style Transfer", + "provider": "bedrock", + "family": "Stable Image Services", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "image" + ] + }, + "capabilities": [ + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Stability AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/stability.stable-style-transfer-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.twelvelabs.pegasus-1-2-v1:0", + "name": "Pegasus v1.2", + "provider": "bedrock", + "family": "Pegasus", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "TwelveLabs", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/twelvelabs.pegasus-1-2-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {} + } + }, + { + "id": "us.writer.palmyra-x4-v1:0", + "name": "Palmyra X4", + "provider": "bedrock", + "family": "palmyra", + "created_at": "2025-04-28 00:00:00 UTC", + "context_window": 122880, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10 + } + } + }, + "metadata": { + "provider_name": "Writer", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/writer.palmyra-x4-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2025-04-28", + "cost": { + "input": 2.5, + "output": 10 + }, + "limit": { + "context": 122880, + "output": 8192 + } + } + }, + { + "id": "us.writer.palmyra-x5-v1:0", + "name": "Palmyra X5", + "provider": "bedrock", + "family": "palmyra", + "created_at": "2025-04-28 00:00:00 UTC", + "context_window": 1040000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 6 + } + } + }, + "metadata": { + "provider_name": "Writer", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/writer.palmyra-x5-v1:0", + "inference_types": [ + "INFERENCE_PROFILE" + ], + "converse": {}, + "source": "models.dev", + "provider_id": "amazon-bedrock", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2025-04-28", + "cost": { + "input": 0.6, + "output": 6 + }, + "limit": { + "context": 1040000, + "output": 8192 + } + } + }, + { + "id": "writer.palmyra-vision-7b", + "name": "Writer Palmyra Vision 7B", + "provider": "bedrock", + "family": "Writer Palmyra Vision", + "created_at": null, + "context_window": null, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "provider_name": "Writer", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/writer.palmyra-vision-7b", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{}", + "maxTokensDefault": null, + "maxTokensMaximum": 4096, + "reasoningSupported": null, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [ + "jpeg", + "png", + "gif", + "webp" + ], + "userVideoTypesSupported": [] + } } }, { @@ -5280,7 +18194,7 @@ "name": "Palmyra X4", "provider": "bedrock", "family": "palmyra", - "created_at": "2025-04-28 00:00:00 +0530", + "created_at": "2025-04-28 00:00:00 UTC", "context_window": 122880, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5326,7 +18240,7 @@ "name": "Palmyra X5", "provider": "bedrock", "family": "palmyra", - "created_at": "2025-04-28 00:00:00 +0530", + "created_at": "2025-04-28 00:00:00 UTC", "context_window": 1040000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5372,7 +18286,7 @@ "name": "GLM-4.7", "provider": "bedrock", "family": "glm", - "created_at": "2025-12-22 00:00:00 +0530", + "created_at": "2025-12-22 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -5386,7 +18300,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -5397,6 +18312,24 @@ } }, "metadata": { + "provider_name": "Z.AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/zai.glm-4.7", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 202752, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -5422,7 +18355,7 @@ "name": "GLM-4.7-Flash", "provider": "bedrock", "family": "glm-flash", - "created_at": "2026-01-19 00:00:00 +0530", + "created_at": "2026-01-19 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -5436,7 +18369,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -5447,6 +18381,24 @@ } }, "metadata": { + "provider_name": "Z.AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/zai.glm-4.7-flash", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 202752, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -5469,7 +18421,7 @@ "name": "GLM-5", "provider": "bedrock", "family": "glm", - "created_at": "2026-03-18 00:00:00 +0530", + "created_at": "2026-03-18 00:00:00 UTC", "context_window": 202752, "max_output_tokens": 101376, "knowledge_cutoff": null, @@ -5483,7 +18435,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -5494,6 +18447,24 @@ } }, "metadata": { + "provider_name": "Z.AI", + "model_arn": "arn:aws:bedrock:us-west-2::foundation-model/zai.glm-5", + "inference_types": [ + "ON_DEMAND" + ], + "converse": { + "additionalRequestFieldsSchema": "{\"reasoningConfig\":{\"enabled\":{\"type\":\"boolean\",\"default\":false}}}", + "maxTokensDefault": null, + "maxTokensMaximum": 202752, + "reasoningSupported": { + "embedded": false + }, + "stopSequencesDefault": [], + "systemRoleSupported": true, + "userDocumentTypesSupported": [], + "userImageTypesSupported": [], + "userVideoTypesSupported": [] + }, "source": "models.dev", "provider_id": "amazon-bedrock", "open_weights": true, @@ -5518,9 +18489,9 @@ "name": "DeepSeek Chat", "provider": "deepseek", "family": "deepseek", - "created_at": "2025-12-01 00:00:00 +0530", - "context_window": 131072, - "max_output_tokens": 8192, + "created_at": "2025-12-01 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 384000, "knowledge_cutoff": null, "modalities": { "input": [ @@ -5536,9 +18507,9 @@ "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.28, - "output_per_million": 0.42, - "cached_input_per_million": 0.028 + "input_per_million": 0.14, + "output_per_million": 0.28, + "cache_read_input_per_million": 0.028 } } }, @@ -5550,13 +18521,13 @@ "temperature": true, "last_updated": "2026-02-28", "cost": { - "input": 0.28, - "output": 0.42, + "input": 0.14, + "output": 0.28, "cache_read": 0.028 }, "limit": { - "context": 131072, - "output": 8192 + "context": 1000000, + "output": 384000 }, "knowledge": "2025-09" } @@ -5566,9 +18537,9 @@ "name": "DeepSeek Reasoner", "provider": "deepseek", "family": "deepseek-thinking", - "created_at": "2025-12-01 00:00:00 +0530", - "context_window": 128000, - "max_output_tokens": 64000, + "created_at": "2025-12-01 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 384000, "knowledge_cutoff": null, "modalities": { "input": [ @@ -5585,9 +18556,9 @@ "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.28, - "output_per_million": 0.42, - "cached_input_per_million": 0.028 + "input_per_million": 0.14, + "output_per_million": 0.28, + "cache_read_input_per_million": 0.028 } } }, @@ -5602,23 +18573,249 @@ "field": "reasoning_content" }, "cost": { - "input": 0.28, - "output": 0.42, + "input": 0.14, + "output": 0.28, "cache_read": 0.028 }, "limit": { - "context": 128000, - "output": 64000 + "context": 1000000, + "output": 384000 }, "knowledge": "2025-09" } }, + { + "id": "deepseek-v4-flash", + "name": "DeepSeek V4 Flash", + "provider": "deepseek", + "family": "deepseek-flash", + "created_at": "2026-04-24 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 384000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.14, + "output_per_million": 0.28, + "cache_read_input_per_million": 0.028 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "deepseek", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-24", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1000000, + "output": 384000 + }, + "knowledge": "2025-05" + } + }, + { + "id": "deepseek-v4-pro", + "name": "DeepSeek V4 Pro", + "provider": "deepseek", + "family": "deepseek-thinking", + "created_at": "2026-04-24 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 384000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.74, + "output_per_million": 3.48, + "cache_read_input_per_million": 0.145 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "deepseek", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-24", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 1.74, + "output": 3.48, + "cache_read": 0.145 + }, + "limit": { + "context": 1000000, + "output": 384000 + }, + "knowledge": "2025-05" + } + }, + { + "id": "aqa", + "name": "Model that performs Attributed Question Answering.", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 7168, + "max_output_tokens": 1024, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": {}, + "metadata": { + "version": "001", + "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.", + "supported_generation_methods": [ + "generateAnswer" + ] + } + }, + { + "id": "deep-research-max-preview-04-2026", + "name": "Deep Research Max Preview (Apr-21-2026)", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "deepthink-exp-05-20", + "description": "Preview release (April 21st, 2026) of Deep Research Max", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, + { + "id": "deep-research-preview-04-2026", + "name": "Deep Research Preview (Apr-21-2026)", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "deepthink-exp-05-20", + "description": "Preview release (April 21th, 2026) of Deep Research", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, + { + "id": "deep-research-pro-preview-12-2025", + "name": "Deep Research Pro Preview (Dec-12-2025)", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "deepthink-exp-05-20", + "description": "Preview release (December 12th, 2025) of Deep Research Pro", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, { "id": "gemini-1.5-flash", "name": "Gemini 1.5 Flash", "provider": "gemini", "family": "gemini-flash", - "created_at": "2024-05-14 00:00:00 +0530", + "created_at": "2024-05-14 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5642,7 +18839,7 @@ "standard": { "input_per_million": 0.075, "output_per_million": 0.3, - "cached_input_per_million": 0.01875 + "cache_read_input_per_million": 0.01875 } } }, @@ -5670,7 +18867,7 @@ "name": "Gemini 1.5 Flash-8B", "provider": "gemini", "family": "gemini-flash", - "created_at": "2024-10-03 00:00:00 +0530", + "created_at": "2024-10-03 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5694,7 +18891,7 @@ "standard": { "input_per_million": 0.0375, "output_per_million": 0.15, - "cached_input_per_million": 0.01 + "cache_read_input_per_million": 0.01 } } }, @@ -5722,7 +18919,7 @@ "name": "Gemini 1.5 Pro", "provider": "gemini", "family": "gemini-pro", - "created_at": "2024-02-15 00:00:00 +0530", + "created_at": "2024-02-15 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5746,7 +18943,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 5, - "cached_input_per_million": 0.3125 + "cache_read_input_per_million": 0.3125 } } }, @@ -5774,7 +18971,7 @@ "name": "Gemini 2.0 Flash", "provider": "gemini", "family": "gemini-flash", - "created_at": "2024-12-11 00:00:00 +0530", + "created_at": "2024-12-11 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5800,11 +18997,19 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "version": "2.0", + "description": "Gemini 2.0 Flash", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -5823,12 +19028,49 @@ "knowledge": "2024-06" } }, + { + "id": "gemini-2.0-flash-001", + "name": "Gemini 2.0 Flash 001", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 1048576, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1, + "output_per_million": 0.4 + } + } + }, + "metadata": { + "version": "2.0", + "description": "Stable version of Gemini 2.0 Flash, our fast and versatile multimodal model for scaling across diverse tasks, released in January of 2025.", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ] + } + }, { "id": "gemini-2.0-flash-lite", "name": "Gemini 2.0 Flash Lite", "provider": "gemini", "family": "gemini-flash-lite", - "created_at": "2024-12-11 00:00:00 +0530", + "created_at": "2024-12-11 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -5858,6 +19100,14 @@ } }, "metadata": { + "version": "2.0", + "description": "Gemini 2.0 Flash-Lite", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -5875,12 +19125,82 @@ "knowledge": "2024-06" } }, + { + "id": "gemini-2.0-flash-lite-001", + "name": "Gemini 2.0 Flash-Lite 001", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 1048576, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "2.0", + "description": "Stable version of Gemini 2.0 Flash-Lite", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ] + } + }, + { + "id": "gemini-2.5-computer-use-preview-10-2025", + "name": "Gemini 2.5 Computer Use Preview 10-2025", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "Gemini 2.5 Computer Use Preview 10-2025", + "description": "Gemini 2.5 Computer Use Preview 10-2025", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, { "id": "gemini-2.5-flash", "name": "Gemini 2.5 Flash", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-03-20 00:00:00 +0530", + "created_at": "2025-03-20 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -5907,7 +19227,7 @@ "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.03 } }, "audio_tokens": { @@ -5917,6 +19237,14 @@ } }, "metadata": { + "version": "001", + "description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -5926,7 +19254,7 @@ "cost": { "input": 0.3, "output": 2.5, - "cache_read": 0.075, + "cache_read": 0.03, "input_audio": 1 }, "limit": { @@ -5941,7 +19269,7 @@ "name": "Gemini 2.5 Flash Image", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-08-26 00:00:00 +0530", + "created_at": "2025-08-26 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -5957,18 +19285,27 @@ }, "capabilities": [ "reasoning", - "vision" + "vision", + "function_calling", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 30, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075 } } }, "metadata": { + "version": "2.0", + "description": "Gemini 2.5 Flash Preview Image", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -5992,7 +19329,7 @@ "name": "Gemini 2.5 Flash Image (Preview)", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-08-26 00:00:00 +0530", + "created_at": "2025-08-26 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -6015,7 +19352,7 @@ "standard": { "input_per_million": 0.3, "output_per_million": 30, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075 } } }, @@ -6043,7 +19380,7 @@ "name": "Gemini 2.5 Flash Lite", "provider": "gemini", "family": "gemini-flash-lite", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6070,11 +19407,19 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "version": "001", + "description": "Stable version of Gemini 2.5 Flash-Lite, released in July of 2025", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6098,7 +19443,7 @@ "name": "Gemini 2.5 Flash Lite Preview 06-17", "provider": "gemini", "family": "gemini-flash-lite", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6124,7 +19469,7 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } }, "audio_tokens": { @@ -6158,7 +19503,7 @@ "name": "Gemini 2.5 Flash Lite Preview 09-25", "provider": "gemini", "family": "gemini-flash-lite", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6185,7 +19530,7 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -6208,12 +19553,117 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-2.5-flash-native-audio-latest", + "name": "Gemini 2.5 Flash Native Audio Latest", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "Gemini 2.5 Flash Native Audio Latest", + "description": "Latest release of Gemini 2.5 Flash Native Audio", + "supported_generation_methods": [ + "countTokens", + "bidiGenerateContent" + ] + } + }, + { + "id": "gemini-2.5-flash-native-audio-preview-09-2025", + "name": "Gemini 2.5 Flash Native Audio Preview 09-2025", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "gemini-2.5-flash-preview-native-audio-dialog-2025-05-19", + "description": "Gemini 2.5 Flash Native Audio Preview 09-2025", + "supported_generation_methods": [ + "countTokens", + "bidiGenerateContent" + ] + } + }, + { + "id": "gemini-2.5-flash-native-audio-preview-12-2025", + "name": "Gemini 2.5 Flash Native Audio Preview 12-2025", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "12-2025", + "description": "Gemini 2.5 Flash Native Audio Preview 12-2025", + "supported_generation_methods": [ + "countTokens", + "bidiGenerateContent" + ] + } + }, { "id": "gemini-2.5-flash-preview-04-17", "name": "Gemini 2.5 Flash Preview 04-17", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-04-17 00:00:00 +0530", + "created_at": "2025-04-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6239,7 +19689,7 @@ "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.0375 + "cache_read_input_per_million": 0.0375 } } }, @@ -6267,7 +19717,7 @@ "name": "Gemini 2.5 Flash Preview 05-20", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6294,7 +19744,7 @@ "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.0375 + "cache_read_input_per_million": 0.0375 } } }, @@ -6322,7 +19772,7 @@ "name": "Gemini 2.5 Flash Preview 09-25", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6349,7 +19799,7 @@ "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075 } }, "audio_tokens": { @@ -6383,7 +19833,7 @@ "name": "Gemini 2.5 Flash Preview TTS", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-05-01 00:00:00 +0530", + "created_at": "2025-05-01 00:00:00 UTC", "context_window": 8000, "max_output_tokens": 16000, "knowledge_cutoff": null, @@ -6395,7 +19845,11 @@ "audio" ] }, - "capabilities": [], + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], "pricing": { "text_tokens": { "standard": { @@ -6405,6 +19859,12 @@ } }, "metadata": { + "version": "gemini-2.5-flash-exp-tts-2025-05-19", + "description": "Gemini 2.5 Flash Preview TTS", + "supported_generation_methods": [ + "countTokens", + "generateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6427,7 +19887,7 @@ "name": "Gemini 2.5 Pro", "provider": "gemini", "family": "gemini-pro", - "created_at": "2025-03-20 00:00:00 +0530", + "created_at": "2025-03-20 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6454,11 +19914,19 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "version": "2.5", + "description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6468,7 +19936,12 @@ "cost": { "input": 1.25, "output": 10, - "cache_read": 0.31 + "cache_read": 0.125, + "context_over_200k": { + "input": 2.5, + "output": 15, + "cache_read": 0.25 + } }, "limit": { "context": 1048576, @@ -6482,7 +19955,7 @@ "name": "Gemini 2.5 Pro Preview 05-06", "provider": "gemini", "family": "gemini-pro", - "created_at": "2025-05-06 00:00:00 +0530", + "created_at": "2025-05-06 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6509,7 +19982,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.31 } } }, @@ -6537,7 +20010,7 @@ "name": "Gemini 2.5 Pro Preview 06-05", "provider": "gemini", "family": "gemini-pro", - "created_at": "2025-06-05 00:00:00 +0530", + "created_at": "2025-06-05 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6564,7 +20037,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.31 } } }, @@ -6592,7 +20065,7 @@ "name": "Gemini 2.5 Pro Preview TTS", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-05-01 00:00:00 +0530", + "created_at": "2025-05-01 00:00:00 UTC", "context_window": 8000, "max_output_tokens": 16000, "knowledge_cutoff": null, @@ -6604,7 +20077,11 @@ "audio" ] }, - "capabilities": [], + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], "pricing": { "text_tokens": { "standard": { @@ -6614,6 +20091,13 @@ } }, "metadata": { + "version": "gemini-2.5-pro-preview-tts-2025-05-19", + "description": "Gemini 2.5 Pro Preview TTS", + "supported_generation_methods": [ + "countTokens", + "generateContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6636,7 +20120,7 @@ "name": "Gemini 3 Flash Preview", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-12-17 00:00:00 +0530", + "created_at": "2025-12-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6663,11 +20147,19 @@ "standard": { "input_per_million": 0.5, "output_per_million": 3, - "cached_input_per_million": 0.05 + "cache_read_input_per_million": 0.05 } } }, "metadata": { + "version": "3-flash-preview-12-2025", + "description": "Gemini 3 Flash Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6691,12 +20183,48 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-3-pro-image-preview", + "name": "Nano Banana Pro", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.0", + "description": "Gemini 3 Pro Image Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "batchGenerateContent" + ] + } + }, { "id": "gemini-3-pro-preview", "name": "Gemini 3 Pro Preview", "provider": "gemini", "family": "gemini-pro", - "created_at": "2025-11-18 00:00:00 +0530", + "created_at": "2025-11-18 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, "knowledge_cutoff": null, @@ -6723,11 +20251,19 @@ "standard": { "input_per_million": 2, "output_per_million": 12, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, "metadata": { + "version": "3-pro-preview-11-2025", + "description": "Gemini 3 Pro Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6756,7 +20292,7 @@ "name": "Gemini 3.1 Flash Image (Preview)", "provider": "gemini", "family": "gemini-flash", - "created_at": "2026-02-26 00:00:00 +0530", + "created_at": "2026-02-26 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -6773,7 +20309,9 @@ }, "capabilities": [ "reasoning", - "vision" + "vision", + "function_calling", + "structured_output" ], "pricing": { "text_tokens": { @@ -6784,6 +20322,13 @@ } }, "metadata": { + "version": "3.0", + "description": "Gemini 3.1 Flash Image Preview.", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6806,7 +20351,7 @@ "name": "Gemini 3.1 Flash Lite Preview", "provider": "gemini", "family": "gemini-flash-lite", - "created_at": "2026-03-03 00:00:00 +0530", + "created_at": "2026-03-03 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6833,11 +20378,20 @@ "standard": { "input_per_million": 0.25, "output_per_million": 1.5, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025, + "cache_write_input_per_million": 1 } } }, "metadata": { + "version": "3.1-flash-lite-preview-03-2026", + "description": "Gemini 3.1 Flash Lite Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6857,12 +20411,82 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-3.1-flash-live-preview", + "name": "Gemini 3.1 Flash Live Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.1-flash-live-03-2026", + "description": "Gemini 3.1 Flash Live Preview", + "supported_generation_methods": [ + "bidiGenerateContent" + ] + } + }, + { + "id": "gemini-3.1-flash-tts-preview", + "name": "Gemini 3.1 Flash TTS Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 8192, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.1-flash-tts-preview", + "description": "Gemini 3.1 Flash TTS Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "batchGenerateContent" + ] + } + }, { "id": "gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro Preview", "provider": "gemini", "family": "gemini-pro", - "created_at": "2026-02-19 00:00:00 +0530", + "created_at": "2026-02-19 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6889,11 +20513,19 @@ "standard": { "input_per_million": 2, "output_per_million": 12, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, "metadata": { + "version": "3.1-pro-preview-01-2026", + "description": "Gemini 3.1 Pro Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6922,7 +20554,7 @@ "name": "Gemini 3.1 Pro Preview Custom Tools", "provider": "gemini", "family": "gemini-pro", - "created_at": "2026-02-19 00:00:00 +0530", + "created_at": "2026-02-19 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -6949,11 +20581,19 @@ "standard": { "input_per_million": 2, "output_per_million": 12, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, "metadata": { + "version": "3.1-pro-preview-01-2026", + "description": "Gemini 3.1 Pro Preview optimized for custom tool usage", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -6982,7 +20622,7 @@ "name": "Gemini Embedding 001", "provider": "gemini", "family": "gemini", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 2048, "max_output_tokens": 3072, "knowledge_cutoff": null, @@ -6991,7 +20631,7 @@ "text" ], "output": [ - "text" + "embeddings" ] }, "capabilities": [], @@ -7003,6 +20643,14 @@ } }, "metadata": { + "version": "001", + "description": "Obtain a distributed representation of a text.", + "supported_generation_methods": [ + "embedContent", + "countTextTokens", + "countTokens", + "asyncBatchEmbedContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -7020,12 +20668,72 @@ "knowledge": "2025-05" } }, + { + "id": "gemini-embedding-2", + "name": "Gemini Embedding 2", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 8192, + "max_output_tokens": 1, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": {}, + "metadata": { + "version": "2", + "description": "Obtain a distributed representation of multimodal content.", + "supported_generation_methods": [ + "embedContent", + "countTextTokens", + "countTokens", + "asyncBatchEmbedContent" + ] + } + }, + { + "id": "gemini-embedding-2-preview", + "name": "Gemini Embedding 2 Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 8192, + "max_output_tokens": 1, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": {}, + "metadata": { + "version": "2", + "description": "Obtain a distributed representation of multimodal content.", + "supported_generation_methods": [ + "embedContent", + "countTextTokens", + "countTokens", + "asyncBatchEmbedContent" + ] + } + }, { "id": "gemini-flash-latest", "name": "Gemini Flash Latest", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -7052,7 +20760,7 @@ "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075 } }, "audio_tokens": { @@ -7062,6 +20770,14 @@ } }, "metadata": { + "version": "Gemini Flash Latest", + "description": "Latest release of Gemini Flash", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -7086,7 +20802,7 @@ "name": "Gemini Flash-Lite Latest", "provider": "gemini", "family": "gemini-flash-lite", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -7113,11 +20829,19 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "version": "Gemini Flash-Lite Latest", + "description": "Latest release of Gemini Flash-Lite", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ], "source": "models.dev", "provider_id": "google", "open_weights": false, @@ -7141,7 +20865,7 @@ "name": "Gemini Live 2.5 Flash", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-09-01 00:00:00 +0530", + "created_at": "2025-09-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 8000, "knowledge_cutoff": null, @@ -7201,7 +20925,7 @@ "name": "Gemini Live 2.5 Flash Preview Native Audio", "provider": "gemini", "family": "gemini-flash", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -7255,12 +20979,121 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-pro-latest", + "name": "Gemini Pro Latest", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "Gemini Pro Latest", + "description": "Latest release of Gemini Pro", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ] + } + }, + { + "id": "gemini-robotics-er-1.5-preview", + "name": "Gemini Robotics-ER 1.5 Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "1.5-preview", + "description": "Gemini Robotics-ER 1.5 Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, + { + "id": "gemini-robotics-er-1.6-preview", + "name": "Gemini Robotics-ER 1.6 Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "1.6-preview", + "description": "Gemini Robotics-ER 1.6 Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "createCachedContent", + "batchGenerateContent" + ] + } + }, { "id": "gemma-3-12b-it", "name": "Gemma 3 12B", "provider": "gemini", "family": "gemma", - "created_at": "2025-03-13 00:00:00 +0530", + "created_at": "2025-03-13 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -7301,7 +21134,7 @@ "name": "Gemma 3 27B", "provider": "gemini", "family": "gemma", - "created_at": "2025-03-12 00:00:00 +0530", + "created_at": "2025-03-12 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -7343,7 +21176,7 @@ "name": "Gemma 3 4B", "provider": "gemini", "family": "gemma", - "created_at": "2025-03-13 00:00:00 +0530", + "created_at": "2025-03-13 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -7383,7 +21216,7 @@ "name": "Gemma 3n 2B", "provider": "gemini", "family": "gemma", - "created_at": "2025-07-09 00:00:00 +0530", + "created_at": "2025-07-09 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 2000, "knowledge_cutoff": null, @@ -7420,7 +21253,7 @@ "name": "Gemma 3n 4B", "provider": "gemini", "family": "gemma", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 2000, "knowledge_cutoff": null, @@ -7453,11 +21286,11 @@ } }, { - "id": "gemma-4-26b-it", + "id": "gemma-4-26b-a4b-it", "name": "Gemma 4 26B", "provider": "gemini", "family": "gemma", - "created_at": "2026-04-02 00:00:00 +0530", + "created_at": "2026-04-02 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -7476,8 +21309,21 @@ "reasoning", "vision" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, "metadata": { + "version": "001", + "description": "Gemma 4 26B A4B IT", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ], "source": "models.dev", "provider_id": "google", "open_weights": true, @@ -7495,7 +21341,7 @@ "name": "Gemma 4 31B", "provider": "gemini", "family": "gemma", - "created_at": "2026-04-02 00:00:00 +0530", + "created_at": "2026-04-02 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -7514,8 +21360,21 @@ "reasoning", "vision" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, "metadata": { + "version": "001", + "description": "Gemma 4 31B IT", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ], "source": "models.dev", "provider_id": "google", "open_weights": true, @@ -7528,12 +21387,472 @@ } } }, + { + "id": "imagen-4.0-fast-generate-001", + "name": "Imagen 4 Fast", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.03, + "output_per_million": 0.03 + } + } + }, + "metadata": { + "version": "001", + "description": "Vertex served Imagen 4.0 Fast model", + "supported_generation_methods": [ + "predict" + ] + } + }, + { + "id": "imagen-4.0-generate-001", + "name": "Imagen 4", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.03, + "output_per_million": 0.03 + } + } + }, + "metadata": { + "version": "001", + "description": "Vertex served Imagen 4.0 model", + "supported_generation_methods": [ + "predict" + ] + } + }, + { + "id": "imagen-4.0-ultra-generate-001", + "name": "Imagen 4 Ultra", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.03, + "output_per_million": 0.03 + } + } + }, + "metadata": { + "version": "001", + "description": "Vertex served Imagen 4.0 ultra model", + "supported_generation_methods": [ + "predict" + ] + } + }, + { + "id": "lyria-3-clip-preview", + "name": "Lyria 3 Clip Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "lyria-3-clip-preview", + "description": "Lyria 3 30s model Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, + { + "id": "lyria-3-pro-preview", + "name": "Lyria 3 Pro Preview", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "lyria-3-pro-preview", + "description": "Lyria 3 Pro Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens" + ] + } + }, + { + "id": "nano-banana-pro-preview", + "name": "Nano Banana Pro", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.0", + "description": "Gemini 3 Pro Image Preview", + "supported_generation_methods": [ + "generateContent", + "countTokens", + "batchGenerateContent" + ] + } + }, + { + "id": "veo-2.0-generate-001", + "name": "Veo 2", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "2.0", + "description": "Vertex served Veo 2 model. Access to this model requires billing to be enabled on the associated Google Cloud Platform account. Please visit https://console.cloud.google.com/billing to enable it.", + "supported_generation_methods": [ + "predictLongRunning" + ] + } + }, + { + "id": "veo-3.0-fast-generate-001", + "name": "Veo 3 fast", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.0", + "description": "Veo 3 fast", + "supported_generation_methods": [ + "predictLongRunning" + ] + } + }, + { + "id": "veo-3.0-generate-001", + "name": "Veo 3", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.0", + "description": "Veo 3", + "supported_generation_methods": [ + "predictLongRunning" + ] + } + }, + { + "id": "veo-3.1-fast-generate-preview", + "name": "Veo 3.1 fast", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.1", + "description": "Veo 3.1 fast", + "supported_generation_methods": [ + "predictLongRunning" + ] + } + }, + { + "id": "veo-3.1-generate-preview", + "name": "Veo 3.1", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.1", + "description": "Veo 3.1", + "supported_generation_methods": [ + "predictLongRunning" + ] + } + }, + { + "id": "veo-3.1-lite-generate-preview", + "name": "Veo 3.1 lite", + "provider": "gemini", + "family": null, + "created_at": null, + "context_window": 480, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "version": "3.1", + "description": "Veo 3.1 lite", + "supported_generation_methods": [ + "predictLongRunning" + ] + } + }, + { + "id": "codestral-2508", + "name": "Codestral", + "provider": "mistral", + "family": "codestral", + "created_at": "2025-08-29 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch", + "predicted_outputs" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "codestral-embed", + "name": "Codestral", + "provider": "mistral", + "family": "codestral", + "created_at": "2025-05-20 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "predicted_outputs" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "codestral-embed-2505", + "name": "Codestral", + "provider": "mistral", + "family": "codestral", + "created_at": "2025-05-20 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [ + "predicted_outputs" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "codestral-latest", "name": "Codestral (latest)", "provider": "mistral", "family": "codestral", - "created_at": "2024-05-29 00:00:00 +0530", + "created_at": "2024-05-29 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -7546,7 +21865,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -7557,6 +21880,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7579,7 +21904,7 @@ "name": "Devstral 2", "provider": "mistral", "family": "devstral", - "created_at": "2025-12-09 00:00:00 +0530", + "created_at": "2025-12-09 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -7592,7 +21917,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -7603,6 +21932,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7620,12 +21951,42 @@ "knowledge": "2025-12" } }, + { + "id": "devstral-latest", + "name": "Devstral Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "devstral-medium-2507", "name": "Devstral Medium", "provider": "mistral", "family": "devstral", - "created_at": "2025-07-10 00:00:00 +0530", + "created_at": "2025-07-10 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -7638,7 +21999,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -7649,6 +22014,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7671,7 +22038,7 @@ "name": "Devstral 2 (latest)", "provider": "mistral", "family": "devstral", - "created_at": "2025-12-02 00:00:00 +0530", + "created_at": "2025-12-02 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -7684,7 +22051,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -7695,6 +22066,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7717,7 +22090,7 @@ "name": "Devstral Small 2505", "provider": "mistral", "family": "devstral", - "created_at": "2025-05-07 00:00:00 +0530", + "created_at": "2025-05-07 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -7763,7 +22136,7 @@ "name": "Devstral Small", "provider": "mistral", "family": "devstral", - "created_at": "2025-07-10 00:00:00 +0530", + "created_at": "2025-07-10 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -7776,7 +22149,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -7787,6 +22164,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7809,7 +22188,7 @@ "name": "Devstral Small 2", "provider": "mistral", "family": "devstral", - "created_at": "2025-12-09 00:00:00 +0530", + "created_at": "2025-12-09 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -7845,12 +22224,71 @@ "knowledge": "2025-12" } }, + { + "id": "labs-leanstral-2603", + "name": "Labs Leanstral 2603", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "magistral-medium-2509", + "name": "Magistral Medium 2509", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "reasoning", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "magistral-medium-latest", "name": "Magistral Medium (latest)", "provider": "mistral", "family": "magistral-medium", - "created_at": "2025-03-17 00:00:00 +0530", + "created_at": "2025-03-17 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -7864,7 +22302,10 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output", + "batch" ], "pricing": { "text_tokens": { @@ -7875,6 +22316,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7897,7 +22340,7 @@ "name": "Magistral Small", "provider": "mistral", "family": "magistral-small", - "created_at": "2025-03-17 00:00:00 +0530", + "created_at": "2025-03-17 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -7939,12 +22382,162 @@ "knowledge": "2025-06" } }, + { + "id": "magistral-small-2509", + "name": "Magistral Small 2509", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "reasoning", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "magistral-small-latest", + "name": "Magistral Small Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "reasoning", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "ministral-14b-2512", + "name": "Ministral 14b 2512", + "provider": "mistral", + "family": "ministral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch", + "distillation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "ministral-14b-latest", + "name": "Ministral 14b Latest", + "provider": "mistral", + "family": "ministral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch", + "distillation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "ministral-3b-2512", + "name": "Ministral 3B", + "provider": "mistral", + "family": "ministral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch", + "distillation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "ministral-3b-latest", "name": "Ministral 3B (latest)", "provider": "mistral", "family": "ministral", - "created_at": "2024-10-01 00:00:00 +0530", + "created_at": "2024-10-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -7957,7 +22550,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "distillation" ], "pricing": { "text_tokens": { @@ -7968,6 +22565,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -7985,12 +22584,42 @@ "knowledge": "2024-10" } }, + { + "id": "ministral-8b-2512", + "name": "Ministral 8B", + "provider": "mistral", + "family": "ministral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch", + "distillation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "ministral-8b-latest", "name": "Ministral 8B (latest)", "provider": "mistral", "family": "ministral", - "created_at": "2024-10-01 00:00:00 +0530", + "created_at": "2024-10-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -8003,7 +22632,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "distillation" ], "pricing": { "text_tokens": { @@ -8014,6 +22647,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8036,7 +22671,7 @@ "name": "Mistral Embed", "provider": "mistral", "family": "mistral-embed", - "created_at": "2023-12-11 00:00:00 +0530", + "created_at": "2023-12-11 00:00:00 UTC", "context_window": 8000, "max_output_tokens": 3072, "knowledge_cutoff": null, @@ -8057,6 +22692,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": false, @@ -8073,12 +22710,36 @@ } } }, + { + "id": "mistral-embed-2312", + "name": "Mistral Embed", + "provider": "mistral", + "family": "mistral-embed", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "embeddings" + ] + }, + "capabilities": [], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "mistral-large-2411", "name": "Mistral Large 2.1", "provider": "mistral", "family": "mistral-large", - "created_at": "2024-11-01 00:00:00 +0530", + "created_at": "2024-11-01 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -8091,7 +22752,11 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8102,6 +22767,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8124,7 +22791,7 @@ "name": "Mistral Large 3", "provider": "mistral", "family": "mistral-large", - "created_at": "2024-11-01 00:00:00 +0530", + "created_at": "2024-11-01 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -8139,7 +22806,11 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8150,6 +22821,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8172,7 +22845,7 @@ "name": "Mistral Large (latest)", "provider": "mistral", "family": "mistral-large", - "created_at": "2024-11-01 00:00:00 +0530", + "created_at": "2024-11-01 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -8187,7 +22860,11 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8198,6 +22875,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8215,12 +22894,75 @@ "knowledge": "2024-11" } }, + { + "id": "mistral-large-pixtral-2411", + "name": "Mistral Large", + "provider": "mistral", + "family": "mistral-large", + "created_at": "2024-11-12 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-medium", + "name": "Mistral Medium", + "provider": "mistral", + "family": "mistral-medium", + "created_at": "2025-05-05 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "mistral-medium-2505", "name": "Mistral Medium 3", "provider": "mistral", "family": "mistral-medium", - "created_at": "2025-05-07 00:00:00 +0530", + "created_at": "2025-05-07 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -8235,7 +22977,11 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8246,6 +22992,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": false, @@ -8268,7 +23016,7 @@ "name": "Mistral Medium 3.1", "provider": "mistral", "family": "mistral-medium", - "created_at": "2025-08-12 00:00:00 +0530", + "created_at": "2025-08-12 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -8283,7 +23031,11 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8294,6 +23046,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": false, @@ -8312,13 +23066,13 @@ } }, { - "id": "mistral-medium-latest", - "name": "Mistral Medium (latest)", + "id": "mistral-medium-2604", + "name": "Mistral Medium 3.5", "provider": "mistral", "family": "mistral-medium", - "created_at": "2025-05-07 00:00:00 +0530", - "context_window": 128000, - "max_output_tokens": 16384, + "created_at": "2026-04-29 00:00:00 UTC", + "context_window": 262144, + "max_output_tokens": 262144, "knowledge_cutoff": null, "modalities": { "input": [ @@ -8331,32 +23085,294 @@ }, "capabilities": [ "function_calling", - "vision" + "structured_output", + "reasoning", + "vision", + "streaming", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.4, - "output_per_million": 2 + "input_per_million": 1.5, + "output_per_million": 7.5 } } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, - "attachment": false, + "attachment": true, "temperature": true, - "last_updated": "2025-05-10", + "last_updated": "2026-04-29", "cost": { - "input": 0.4, - "output": 2 + "input": 1.5, + "output": 7.5 }, "limit": { - "context": 128000, - "output": 16384 + "context": 262144, + "output": 262144 + } + } + }, + { + "id": "mistral-medium-3", + "name": "Mistral Medium", + "provider": "mistral", + "family": "mistral-medium", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-medium-3-5", + "name": "Mistral Medium", + "provider": "mistral", + "family": "mistral-medium", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-medium-3.5", + "name": "Mistral Medium", + "provider": "mistral", + "family": "mistral-medium", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-medium-c21211-r0-75", + "name": "Mistral Medium", + "provider": "mistral", + "family": "mistral-medium", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch", + "fine_tuning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-medium-latest", + "name": "Mistral Medium (latest)", + "provider": "mistral", + "family": "mistral-medium", + "created_at": "2026-04-29 00:00:00 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming", + "batch", + "fine_tuning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.5, + "output_per_million": 7.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "mistralai", + "source": "models.dev", + "provider_id": "mistral", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-29", + "cost": { + "input": 1.5, + "output": 7.5 }, - "knowledge": "2025-05" + "limit": { + "context": 262144, + "output": 262144 + } + } + }, + { + "id": "mistral-moderation-2411", + "name": "Mistral Moderation", + "provider": "mistral", + "family": "mistral-moderation", + "created_at": "2024-11-26 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "moderation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-moderation-2603", + "name": "Mistral Moderation", + "provider": "mistral", + "family": "mistral-moderation", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "moderation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-moderation-latest", + "name": "Mistral Moderation", + "provider": "mistral", + "family": "mistral-moderation", + "created_at": "2024-11-26 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "moderation" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" } }, { @@ -8364,7 +23380,7 @@ "name": "Mistral Nemo", "provider": "mistral", "family": "mistral-nemo", - "created_at": "2024-07-01 00:00:00 +0530", + "created_at": "2024-07-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -8405,12 +23421,90 @@ "knowledge": "2024-07" } }, + { + "id": "mistral-ocr-2505", + "name": "Mistral Ocr 2505", + "provider": "mistral", + "family": "mistral", + "created_at": "2025-05-22 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-ocr-2512", + "name": "Mistral Ocr 2512", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-ocr-latest", + "name": "Mistral Ocr Latest", + "provider": "mistral", + "family": "mistral", + "created_at": "2025-05-22 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "mistral-small-2506", "name": "Mistral Small 3.2", "provider": "mistral", "family": "mistral-small", - "created_at": "2025-06-20 00:00:00 +0530", + "created_at": "2025-06-20 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -8425,7 +23519,11 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8436,6 +23534,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8458,7 +23558,7 @@ "name": "Mistral Small 4", "provider": "mistral", "family": "mistral-small", - "created_at": "2026-03-16 00:00:00 +0530", + "created_at": "2026-03-16 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -8474,7 +23574,11 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8485,6 +23589,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8507,7 +23613,7 @@ "name": "Mistral Small (latest)", "provider": "mistral", "family": "mistral-small", - "created_at": "2026-03-16 00:00:00 +0530", + "created_at": "2026-03-16 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -8523,7 +23629,11 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming", + "structured_output", + "batch", + "fine_tuning" ], "pricing": { "text_tokens": { @@ -8534,6 +23644,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8551,12 +23663,157 @@ "knowledge": "2025-06" } }, + { + "id": "mistral-tiny-2407", + "name": "Mistral Tiny 2407", + "provider": "mistral", + "family": "mistral", + "created_at": "2024-07-17 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-tiny-latest", + "name": "Mistral Tiny Latest", + "provider": "mistral", + "family": "mistral", + "created_at": "2024-07-17 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-vibe-cli-fast", + "name": "Mistral Vibe Cli Fast", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-vibe-cli-latest", + "name": "Mistral Vibe Cli Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "mistral-vibe-cli-with-tools", + "name": "Mistral Vibe Cli With Tools", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "open-mistral-7b", "name": "Mistral 7B", "provider": "mistral", "family": "mistral", - "created_at": "2023-09-27 00:00:00 +0530", + "created_at": "2023-09-27 00:00:00 UTC", "context_window": 8000, "max_output_tokens": 8000, "knowledge_cutoff": null, @@ -8597,12 +23854,70 @@ "knowledge": "2023-12" } }, + { + "id": "open-mistral-nemo", + "name": "Open Mistral Nemo", + "provider": "mistral", + "family": "mistral", + "created_at": "2024-07-17 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "open-mistral-nemo-2407", + "name": "Open Mistral Nemo 2407", + "provider": "mistral", + "family": "mistral", + "created_at": "2024-07-17 23:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "open-mixtral-8x22b", "name": "Mixtral 8x22B", "provider": "mistral", "family": "mixtral", - "created_at": "2024-04-17 00:00:00 +0530", + "created_at": "2024-04-17 00:00:00 UTC", "context_window": 64000, "max_output_tokens": 64000, "knowledge_cutoff": null, @@ -8648,7 +23963,7 @@ "name": "Mixtral 8x7B", "provider": "mistral", "family": "mixtral", - "created_at": "2023-12-11 00:00:00 +0530", + "created_at": "2023-12-11 00:00:00 UTC", "context_window": 32000, "max_output_tokens": 32000, "knowledge_cutoff": null, @@ -8694,7 +24009,7 @@ "name": "Pixtral 12B", "provider": "mistral", "family": "pixtral", - "created_at": "2024-09-01 00:00:00 +0530", + "created_at": "2024-09-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -8737,12 +24052,43 @@ "knowledge": "2024-09" } }, + { + "id": "pixtral-large-2411", + "name": "Pixtral Large", + "provider": "mistral", + "family": "pixtral", + "created_at": "2024-11-12 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision", + "batch" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, { "id": "pixtral-large-latest", "name": "Pixtral Large (latest)", "provider": "mistral", "family": "pixtral", - "created_at": "2024-11-01 00:00:00 +0530", + "created_at": "2024-11-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -8757,7 +24103,10 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming", + "structured_output", + "batch" ], "pricing": { "text_tokens": { @@ -8768,6 +24117,8 @@ } }, "metadata": { + "object": "model", + "owned_by": "mistralai", "source": "models.dev", "provider_id": "mistral", "open_weights": true, @@ -8786,13 +24137,13 @@ } }, { - "id": "babbage-002", - "name": "Babbage 002", - "provider": "openai", - "family": "babbage", - "created_at": "2023-08-21 21:46:55 +0530", - "context_window": 4096, - "max_output_tokens": 16384, + "id": "voxtral-mini-2507", + "name": "Voxtral Mini 2507", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, "knowledge_cutoff": null, "modalities": { "input": [ @@ -8805,6 +24156,286 @@ "capabilities": [ "streaming" ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-2602", + "name": "Voxtral Mini 2602", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-latest", + "name": "Voxtral Mini Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-realtime-2602", + "name": "Voxtral Mini Realtime 2602", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-realtime-latest", + "name": "Voxtral Mini Realtime Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-transcribe-2507", + "name": "Voxtral Mini Transcribe 2507", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "transcription" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-transcribe-realtime-2602", + "name": "Voxtral Mini Transcribe Realtime 2602", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "transcription" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-tts-2603", + "name": "Voxtral Mini Tts 2603", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-mini-tts-latest", + "name": "Voxtral Mini Tts Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-small-2507", + "name": "Voxtral Small 2507", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "voxtral-small-latest", + "name": "Voxtral Small Latest", + "provider": "mistral", + "family": "mistral", + "created_at": null, + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "mistralai" + } + }, + { + "id": "babbage-002", + "name": "babbage-002", + "provider": "openai", + "family": null, + "created_at": "2023-08-21 16:16:55 UTC", + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -8818,12 +24449,39 @@ "owned_by": "system" } }, + { + "id": "chat-latest", + "name": "chat-latest", + "provider": "openai", + "family": null, + "created_at": "2026-05-02 06:50:02 UTC", + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system" + } + }, { "id": "chatgpt-image-latest", "name": "chatgpt-image-latest", "provider": "openai", "family": "gpt-image", - "created_at": "2025-12-16 00:00:00 +0530", + "created_at": "2025-12-16 00:00:00 UTC", "context_window": 0, "max_output_tokens": 0, "knowledge_cutoff": null, @@ -8838,10 +24496,16 @@ ] }, "capabilities": [ - "vision", - "streaming" + "vision" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, "metadata": { "object": "model", "owned_by": "system", @@ -8858,75 +24522,20 @@ } } }, - { - "id": "codex-mini-latest", - "name": "Codex Mini", - "provider": "openai", - "family": "gpt-codex-mini", - "created_at": "2025-05-16 00:00:00 +0530", - "context_window": 200000, - "max_output_tokens": 100000, - "knowledge_cutoff": null, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "capabilities": [ - "function_calling", - "reasoning" - ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 1.5, - "output_per_million": 6, - "cached_input_per_million": 0.375 - } - } - }, - "metadata": { - "source": "models.dev", - "provider_id": "openai", - "open_weights": false, - "attachment": true, - "temperature": false, - "last_updated": "2025-05-16", - "cost": { - "input": 1.5, - "output": 6, - "cache_read": 0.375 - }, - "limit": { - "context": 200000, - "output": 100000 - }, - "knowledge": "2024-04" - } - }, { "id": "computer-use-preview", - "name": "Computer Use Preview", + "name": "computer-use-preview", "provider": "openai", - "family": "other", - "created_at": "2024-12-20 06:17:57 +0530", + "family": null, + "created_at": "2024-12-20 00:47:57 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -8942,24 +24551,18 @@ }, { "id": "computer-use-preview-2025-03-11", - "name": "Computer Use Preview 20250311", + "name": "computer-use-preview-2025-03-11", "provider": "openai", - "family": "other", - "created_at": "2025-03-08 01:20:21 +0530", + "family": null, + "created_at": "2025-03-07 19:50:21 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -8975,25 +24578,18 @@ }, { "id": "dall-e-2", - "name": "DALL-E-2", + "name": "dall-e-2", "provider": "openai", - "family": "dall_e", - "created_at": "2023-11-01 05:52:57 +0530", + "family": null, + "created_at": "2023-11-01 00:22:57 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text", - "image" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9009,25 +24605,18 @@ }, { "id": "dall-e-3", - "name": "DALL-E-3", + "name": "dall-e-3", "provider": "openai", - "family": "dall_e", - "created_at": "2023-11-01 02:16:29 +0530", + "family": null, + "created_at": "2023-10-31 20:46:29 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text", - "image" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9043,24 +24632,18 @@ }, { "id": "davinci-002", - "name": "Davinci 002", + "name": "davinci-002", "provider": "openai", - "family": "davinci", - "created_at": "2023-08-21 21:41:41 +0530", + "family": null, + "created_at": "2023-08-21 16:11:41 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9079,7 +24662,7 @@ "name": "GPT-3.5-turbo", "provider": "openai", "family": "gpt", - "created_at": "2023-03-01 00:00:00 +0530", + "created_at": "2023-03-01 00:00:00 UTC", "context_window": 16385, "max_output_tokens": 4096, "knowledge_cutoff": "2021-09-01", @@ -9091,15 +24674,13 @@ "text" ] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.5, "output_per_million": 1.5, - "cached_input_per_million": 1.25 + "cache_read_input_per_million": 1.25 } } }, @@ -9126,24 +24707,18 @@ }, { "id": "gpt-3.5-turbo-0125", - "name": "GPT-3.5 Turbo 0125", + "name": "gpt-3.5-turbo-0125", "provider": "openai", - "family": "gpt35_turbo", - "created_at": "2024-01-24 03:49:18 +0530", + "family": null, + "created_at": "2024-01-23 22:19:18 UTC", "context_window": 16385, "max_output_tokens": 4096, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9159,24 +24734,18 @@ }, { "id": "gpt-3.5-turbo-1106", - "name": "GPT-3.5 Turbo 1106", + "name": "gpt-3.5-turbo-1106", "provider": "openai", - "family": "gpt35_turbo", - "created_at": "2023-11-03 02:45:48 +0530", + "family": null, + "created_at": "2023-11-02 21:15:48 UTC", "context_window": 16385, "max_output_tokens": 4096, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9192,24 +24761,18 @@ }, { "id": "gpt-3.5-turbo-16k", - "name": "GPT-3.5 Turbo 16k", + "name": "gpt-3.5-turbo-16k", "provider": "openai", - "family": "gpt35_turbo", - "created_at": "2023-05-11 04:05:02 +0530", + "family": null, + "created_at": "2023-05-10 22:35:02 UTC", "context_window": 16385, "max_output_tokens": 4096, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9225,24 +24788,18 @@ }, { "id": "gpt-3.5-turbo-instruct", - "name": "GPT-3.5 Turbo Instruct", + "name": "gpt-3.5-turbo-instruct", "provider": "openai", - "family": "gpt35_turbo", - "created_at": "2023-08-24 23:53:47 +0530", + "family": null, + "created_at": "2023-08-24 18:23:47 UTC", "context_window": 16385, "max_output_tokens": 4096, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9258,24 +24815,18 @@ }, { "id": "gpt-3.5-turbo-instruct-0914", - "name": "GPT-3.5 Turbo Instruct 0914", + "name": "gpt-3.5-turbo-instruct-0914", "provider": "openai", - "family": "gpt35_turbo", - "created_at": "2023-09-08 03:04:32 +0530", + "family": null, + "created_at": "2023-09-07 21:34:32 UTC", "context_window": 16385, "max_output_tokens": 4096, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9294,7 +24845,7 @@ "name": "GPT-4", "provider": "openai", "family": "gpt", - "created_at": "2023-11-06 00:00:00 +0530", + "created_at": "2023-11-06 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -9308,7 +24859,7 @@ }, "capabilities": [ "function_calling", - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -9340,24 +24891,18 @@ }, { "id": "gpt-4-0613", - "name": "GPT-4 0613", + "name": "gpt-4-0613", "provider": "openai", - "family": "other", - "created_at": "2023-06-12 22:24:56 +0530", + "family": null, + "created_at": "2023-06-12 16:54:56 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9376,7 +24921,7 @@ "name": "GPT-4 Turbo", "provider": "openai", "family": "gpt", - "created_at": "2023-11-06 00:00:00 +0530", + "created_at": "2023-11-06 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -9391,8 +24936,7 @@ }, "capabilities": [ "function_calling", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -9424,26 +24968,20 @@ }, { "id": "gpt-4-turbo-2024-04-09", - "name": "GPT-4 Turbo 20240409", + "name": "gpt-4-turbo-2024-04-09", "provider": "openai", - "family": "gpt4_turbo", - "created_at": "2024-04-09 00:11:17 +0530", + "family": null, + "created_at": "2024-04-08 18:41:17 UTC", "context_window": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", - "function_calling" + "function_calling", + "vision" ], "pricing": { "text_tokens": { @@ -9463,7 +25001,7 @@ "name": "GPT-4.1", "provider": "openai", "family": "gpt", - "created_at": "2025-04-14 00:00:00 +0530", + "created_at": "2025-04-14 00:00:00 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -9480,15 +25018,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2, "output_per_million": 8, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5 } } }, @@ -9515,34 +25052,28 @@ }, { "id": "gpt-4.1-2025-04-14", - "name": "GPT-4.1 20250414", + "name": "gpt-4.1-2025-04-14", "provider": "openai", - "family": "gpt41", - "created_at": "2025-04-11 01:39:06 +0530", + "family": null, + "created_at": "2025-04-10 20:09:06 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", - "structured_output" + "structured_output", + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2.0, "output_per_million": 8.0, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5 } } }, @@ -9556,7 +25087,7 @@ "name": "GPT-4.1 mini", "provider": "openai", "family": "gpt-mini", - "created_at": "2025-04-14 00:00:00 +0530", + "created_at": "2025-04-14 00:00:00 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -9573,15 +25104,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.4, "output_per_million": 1.6, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1 } } }, @@ -9608,34 +25138,28 @@ }, { "id": "gpt-4.1-mini-2025-04-14", - "name": "GPT-4.1 Mini 20250414", + "name": "gpt-4.1-mini-2025-04-14", "provider": "openai", - "family": "gpt41_mini", - "created_at": "2025-04-11 02:09:07 +0530", + "family": null, + "created_at": "2025-04-10 20:39:07 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", - "structured_output" + "structured_output", + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.4, "output_per_million": 1.6, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1 } } }, @@ -9649,7 +25173,7 @@ "name": "GPT-4.1 nano", "provider": "openai", "family": "gpt-nano", - "created_at": "2025-04-14 00:00:00 +0530", + "created_at": "2025-04-14 00:00:00 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -9665,15 +25189,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.03 + "cache_read_input_per_million": 0.03 } } }, @@ -9700,27 +25223,21 @@ }, { "id": "gpt-4.1-nano-2025-04-14", - "name": "GPT-4.1 Nano 20250414", + "name": "gpt-4.1-nano-2025-04-14", "provider": "openai", - "family": "gpt41_nano", - "created_at": "2025-04-11 03:07:05 +0530", + "family": null, + "created_at": "2025-04-10 21:37:05 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", - "structured_output" + "structured_output", + "vision" ], "pricing": { "text_tokens": { @@ -9740,7 +25257,7 @@ "name": "GPT-4o", "provider": "openai", "family": "gpt", - "created_at": "2024-05-13 00:00:00 +0530", + "created_at": "2024-05-13 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -9757,15 +25274,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2.5, "output_per_million": 10, - "cached_input_per_million": 1.25 + "cache_read_input_per_million": 1.25 } } }, @@ -9795,7 +25311,7 @@ "name": "GPT-4o (2024-05-13)", "provider": "openai", "family": "gpt", - "created_at": "2024-05-13 00:00:00 +0530", + "created_at": "2024-05-13 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -9811,8 +25327,7 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -9847,7 +25362,7 @@ "name": "GPT-4o (2024-08-06)", "provider": "openai", "family": "gpt", - "created_at": "2024-08-06 00:00:00 +0530", + "created_at": "2024-08-06 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -9863,15 +25378,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2.5, "output_per_million": 10, - "cached_input_per_million": 1.25 + "cache_read_input_per_million": 1.25 } } }, @@ -9901,7 +25415,7 @@ "name": "GPT-4o (2024-11-20)", "provider": "openai", "family": "gpt", - "created_at": "2024-11-20 00:00:00 +0530", + "created_at": "2024-11-20 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -9917,15 +25431,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2.5, "output_per_million": 10, - "cached_input_per_million": 1.25 + "cache_read_input_per_million": 1.25 } } }, @@ -9952,28 +25465,18 @@ }, { "id": "gpt-4o-audio-preview", - "name": "GPT-4o-Audio Preview", + "name": "gpt-4o-audio-preview", "provider": "openai", - "family": "gpt4o_audio", - "created_at": "2024-09-27 23:37:23 +0530", + "family": null, + "created_at": "2024-09-27 18:07:23 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming", - "speech_generation", - "transcription" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -9989,28 +25492,18 @@ }, { "id": "gpt-4o-audio-preview-2024-12-17", - "name": "GPT-4o-Audio Preview 20241217", + "name": "gpt-4o-audio-preview-2024-12-17", "provider": "openai", - "family": "gpt4o_audio", - "created_at": "2024-12-13 01:40:39 +0530", + "family": null, + "created_at": "2024-12-12 20:10:39 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming", - "speech_generation", - "transcription" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10026,28 +25519,18 @@ }, { "id": "gpt-4o-audio-preview-2025-06-03", - "name": "GPT-4o-Audio Preview 20250603", + "name": "gpt-4o-audio-preview-2025-06-03", "provider": "openai", - "family": "gpt4o_audio", - "created_at": "2025-06-03 05:24:58 +0530", + "family": null, + "created_at": "2025-06-02 23:54:58 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming", - "speech_generation", - "transcription" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10066,7 +25549,7 @@ "name": "GPT-4o mini", "provider": "openai", "family": "gpt-mini", - "created_at": "2024-07-18 00:00:00 +0530", + "created_at": "2024-07-18 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -10083,15 +25566,14 @@ "capabilities": [ "function_calling", "structured_output", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08 } } }, @@ -10118,27 +25600,21 @@ }, { "id": "gpt-4o-mini-2024-07-18", - "name": "GPT-4o-Mini 20240718", + "name": "gpt-4o-mini-2024-07-18", "provider": "openai", - "family": "gpt4o_mini", - "created_at": "2024-07-17 05:01:57 +0530", + "family": null, + "created_at": "2024-07-16 23:31:57 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", - "structured_output" + "structured_output", + "vision" ], "pricing": { "text_tokens": { @@ -10155,28 +25631,18 @@ }, { "id": "gpt-4o-mini-audio-preview", - "name": "GPT-4o-Mini Audio Preview", + "name": "gpt-4o-mini-audio-preview", "provider": "openai", - "family": "gpt4o_mini_audio", - "created_at": "2024-12-17 03:47:04 +0530", + "family": null, + "created_at": "2024-12-16 22:17:04 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming", - "speech_generation", - "transcription" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10192,28 +25658,18 @@ }, { "id": "gpt-4o-mini-audio-preview-2024-12-17", - "name": "GPT-4o-Mini Audio Preview 20241217", + "name": "gpt-4o-mini-audio-preview-2024-12-17", "provider": "openai", - "family": "gpt4o_mini_audio", - "created_at": "2024-12-14 00:22:00 +0530", + "family": null, + "created_at": "2024-12-13 18:52:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming", - "speech_generation", - "transcription" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10229,24 +25685,18 @@ }, { "id": "gpt-4o-mini-realtime-preview", - "name": "GPT-4o-Mini Realtime Preview", + "name": "gpt-4o-mini-realtime-preview", "provider": "openai", - "family": "gpt4o_mini_realtime", - "created_at": "2024-12-17 03:46:20 +0530", + "family": null, + "created_at": "2024-12-16 22:16:20 UTC", "context_window": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10262,24 +25712,18 @@ }, { "id": "gpt-4o-mini-realtime-preview-2024-12-17", - "name": "GPT-4o-Mini Realtime Preview 20241217", + "name": "gpt-4o-mini-realtime-preview-2024-12-17", "provider": "openai", - "family": "gpt4o_mini_realtime", - "created_at": "2024-12-13 23:26:41 +0530", + "family": null, + "created_at": "2024-12-13 17:56:41 UTC", "context_window": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10295,24 +25739,18 @@ }, { "id": "gpt-4o-mini-search-preview", - "name": "GPT-4o-Mini Search Preview", + "name": "gpt-4o-mini-search-preview", "provider": "openai", - "family": "other", - "created_at": "2025-03-08 05:16:01 +0530", + "family": null, + "created_at": "2025-03-07 23:46:01 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10328,24 +25766,18 @@ }, { "id": "gpt-4o-mini-search-preview-2025-03-11", - "name": "GPT-4o-Mini Search Preview 20250311", + "name": "gpt-4o-mini-search-preview-2025-03-11", "provider": "openai", - "family": "other", - "created_at": "2025-03-08 05:10:58 +0530", + "family": null, + "created_at": "2025-03-07 23:40:58 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10361,25 +25793,18 @@ }, { "id": "gpt-4o-mini-transcribe", - "name": "GPT-4o-Mini Transcribe", + "name": "gpt-4o-mini-transcribe", "provider": "openai", - "family": "gpt4o_mini_transcribe", - "created_at": "2025-03-16 01:26:36 +0530", + "family": null, + "created_at": "2025-03-15 19:56:36 UTC", "context_window": 16000, "max_output_tokens": 2000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10395,25 +25820,18 @@ }, { "id": "gpt-4o-mini-transcribe-2025-03-20", - "name": "GPT-4o-Mini Transcribe 20250320", + "name": "gpt-4o-mini-transcribe-2025-03-20", "provider": "openai", - "family": "gpt4o_mini_transcribe", - "created_at": "2025-12-13 12:52:25 +0530", + "family": null, + "created_at": "2025-12-13 07:22:25 UTC", "context_window": 16000, "max_output_tokens": 2000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10429,25 +25847,18 @@ }, { "id": "gpt-4o-mini-transcribe-2025-12-15", - "name": "GPT-4o-Mini Transcribe 20251215", + "name": "gpt-4o-mini-transcribe-2025-12-15", "provider": "openai", - "family": "gpt4o_mini_transcribe", - "created_at": "2025-12-13 12:50:07 +0530", + "family": null, + "created_at": "2025-12-13 07:20:07 UTC", "context_window": 16000, "max_output_tokens": 2000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10463,26 +25874,18 @@ }, { "id": "gpt-4o-mini-tts", - "name": "GPT-4o-Mini Tts", + "name": "gpt-4o-mini-tts", "provider": "openai", - "family": "gpt4o_mini_tts", - "created_at": "2025-03-19 22:35:59 +0530", + "family": null, + "created_at": "2025-03-19 17:05:59 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10498,26 +25901,18 @@ }, { "id": "gpt-4o-mini-tts-2025-03-20", - "name": "GPT-4o-Mini Tts 20250320", + "name": "gpt-4o-mini-tts-2025-03-20", "provider": "openai", - "family": "gpt4o_mini_tts", - "created_at": "2025-12-13 12:55:31 +0530", + "family": null, + "created_at": "2025-12-13 07:25:31 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10533,26 +25928,18 @@ }, { "id": "gpt-4o-mini-tts-2025-12-15", - "name": "GPT-4o-Mini Tts 20251215", + "name": "gpt-4o-mini-tts-2025-12-15", "provider": "openai", - "family": "gpt4o_mini_tts", - "created_at": "2025-12-13 12:57:17 +0530", + "family": null, + "created_at": "2025-12-13 07:27:17 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10568,24 +25955,18 @@ }, { "id": "gpt-4o-realtime-preview", - "name": "GPT-4o-Realtime Preview", + "name": "gpt-4o-realtime-preview", "provider": "openai", - "family": "gpt4o_realtime", - "created_at": "2024-09-30 07:03:18 +0530", + "family": null, + "created_at": "2024-09-30 01:33:18 UTC", "context_window": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10601,24 +25982,18 @@ }, { "id": "gpt-4o-realtime-preview-2024-12-17", - "name": "GPT-4o-Realtime Preview 20241217", + "name": "gpt-4o-realtime-preview-2024-12-17", "provider": "openai", - "family": "gpt4o_realtime", - "created_at": "2024-12-12 01:00:30 +0530", + "family": null, + "created_at": "2024-12-11 19:30:30 UTC", "context_window": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10634,24 +26009,18 @@ }, { "id": "gpt-4o-realtime-preview-2025-06-03", - "name": "GPT-4o-Realtime Preview 20250603", + "name": "gpt-4o-realtime-preview-2025-06-03", "provider": "openai", - "family": "gpt4o_realtime", - "created_at": "2025-06-03 05:13:58 +0530", + "family": null, + "created_at": "2025-06-02 23:43:58 UTC", "context_window": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10667,25 +26036,19 @@ }, { "id": "gpt-4o-search-preview", - "name": "GPT-4o Search Preview", + "name": "gpt-4o-search-preview", "provider": "openai", - "family": "gpt4o_search", - "created_at": "2026-02-24 09:28:54 +0530", + "family": null, + "created_at": "2026-02-24 03:58:54 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -10702,25 +26065,19 @@ }, { "id": "gpt-4o-search-preview-2025-03-11", - "name": "GPT-4o Search Preview 20250311", + "name": "gpt-4o-search-preview-2025-03-11", "provider": "openai", - "family": "gpt4o_search", - "created_at": "2026-02-24 09:30:21 +0530", + "family": null, + "created_at": "2026-02-24 04:00:21 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -10737,25 +26094,18 @@ }, { "id": "gpt-4o-transcribe", - "name": "GPT-4o-Transcribe", + "name": "gpt-4o-transcribe", "provider": "openai", - "family": "gpt4o_transcribe", - "created_at": "2025-03-16 01:24:23 +0530", + "family": null, + "created_at": "2025-03-15 19:54:23 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10771,25 +26121,18 @@ }, { "id": "gpt-4o-transcribe-diarize", - "name": "GPT-4o-Transcribe Diarize", + "name": "gpt-4o-transcribe-diarize", "provider": "openai", - "family": "gpt4o_transcribe", - "created_at": "2025-06-25 02:31:27 +0530", + "family": null, + "created_at": "2025-06-24 21:01:27 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -10808,7 +26151,7 @@ "name": "GPT-5", "provider": "openai", "family": "gpt", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -10825,15 +26168,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -10861,27 +26203,21 @@ }, { "id": "gpt-5-2025-08-07", - "name": "GPT-5 20250807", + "name": "gpt-5-2025-08-07", "provider": "openai", - "family": "gpt5", - "created_at": "2025-08-02 00:39:20 +0530", + "family": null, + "created_at": "2025-08-01 19:09:20 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -10889,7 +26225,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -10903,7 +26239,7 @@ "name": "GPT-5 Chat (latest)", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -10920,7 +26256,6 @@ "structured_output", "reasoning", "vision", - "streaming", "function_calling" ], "pricing": { @@ -10957,7 +26292,7 @@ "name": "GPT-5-Codex", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-09-15 00:00:00 +0530", + "created_at": "2025-09-15 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -10974,15 +26309,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11013,7 +26347,7 @@ "name": "GPT-5 Mini", "provider": "openai", "family": "gpt-mini", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-05-30", @@ -11030,15 +26364,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.25, "output_per_million": 2, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -11066,35 +26399,29 @@ }, { "id": "gpt-5-mini-2025-08-07", - "name": "GPT-5 Mini 20250807", + "name": "gpt-5-mini-2025-08-07", "provider": "openai", - "family": "gpt5", - "created_at": "2025-08-06 02:01:07 +0530", + "family": null, + "created_at": "2025-08-05 20:31:07 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 1.25, - "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 } } }, @@ -11108,7 +26435,7 @@ "name": "GPT-5 Nano", "provider": "openai", "family": "gpt-nano", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-05-30", @@ -11125,15 +26452,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.05, "output_per_million": 0.4, - "cached_input_per_million": 0.005 + "cache_read_input_per_million": 0.005 } } }, @@ -11161,35 +26487,29 @@ }, { "id": "gpt-5-nano-2025-08-07", - "name": "GPT-5 Nano 20250807", + "name": "gpt-5-nano-2025-08-07", "provider": "openai", - "family": "gpt5", - "created_at": "2025-08-06 02:08:23 +0530", + "family": null, + "created_at": "2025-08-05 20:38:23 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 1.25, - "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "input_per_million": 0.05, + "output_per_million": 0.4, + "cache_read_input_per_million": 0.005 } } }, @@ -11203,7 +26523,7 @@ "name": "GPT-5 Pro", "provider": "openai", "family": "gpt-pro", - "created_at": "2025-10-06 00:00:00 +0530", + "created_at": "2025-10-06 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 272000, "knowledge_cutoff": "2024-09-30", @@ -11220,8 +26540,7 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -11254,27 +26573,21 @@ }, { "id": "gpt-5-pro-2025-10-06", - "name": "GPT-5 Pro 20251006", + "name": "gpt-5-pro-2025-10-06", "provider": "openai", - "family": "gpt5", - "created_at": "2025-10-03 11:05:07 +0530", + "family": null, + "created_at": "2025-10-03 05:35:07 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -11282,7 +26595,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11293,27 +26606,21 @@ }, { "id": "gpt-5-search-api", - "name": "GPT-5 Search Api", + "name": "gpt-5-search-api", "provider": "openai", - "family": "gpt5", - "created_at": "2025-10-03 23:33:49 +0530", + "family": null, + "created_at": "2025-10-03 18:03:49 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -11321,7 +26628,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11332,27 +26639,21 @@ }, { "id": "gpt-5-search-api-2025-10-14", - "name": "GPT-5 Search Api 20251014", + "name": "gpt-5-search-api-2025-10-14", "provider": "openai", - "family": "gpt5", - "created_at": "2025-10-10 02:36:00 +0530", + "family": null, + "created_at": "2025-10-09 21:06:00 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -11360,7 +26661,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11374,7 +26675,7 @@ "name": "GPT-5.1", "provider": "openai", "family": "gpt", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -11391,15 +26692,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.13 + "cache_read_input_per_million": 0.13 } } }, @@ -11427,27 +26727,21 @@ }, { "id": "gpt-5.1-2025-11-13", - "name": "GPT-5.1 20251113", + "name": "gpt-5.1-2025-11-13", "provider": "openai", - "family": "gpt5", - "created_at": "2025-11-11 00:15:53 +0530", + "family": null, + "created_at": "2025-11-10 18:45:53 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -11455,7 +26749,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11469,7 +26763,7 @@ "name": "GPT-5.1 Chat", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": "2024-09-30", @@ -11486,15 +26780,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11524,7 +26817,7 @@ "name": "GPT-5.1 Codex", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -11541,15 +26834,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11580,7 +26872,7 @@ "name": "GPT-5.1 Codex Max", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -11597,15 +26889,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11636,7 +26927,7 @@ "name": "GPT-5.1 Codex mini", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -11653,15 +26944,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.25, "output_per_million": 2, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -11692,7 +26982,7 @@ "name": "GPT-5.2", "provider": "openai", "family": "gpt", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -11709,15 +26999,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, @@ -11745,27 +27034,21 @@ }, { "id": "gpt-5.2-2025-12-11", - "name": "GPT-5.2 20251211", + "name": "gpt-5.2-2025-12-11", "provider": "openai", - "family": "gpt5", - "created_at": "2025-12-10 02:13:48 +0530", + "family": null, + "created_at": "2025-12-09 20:43:48 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -11773,7 +27056,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11787,7 +27070,7 @@ "name": "GPT-5.2 Chat", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": "2025-08-31", @@ -11804,15 +27087,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, @@ -11842,7 +27124,7 @@ "name": "GPT-5.2 Codex", "provider": "openai", "family": "gpt-codex", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -11860,15 +27142,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, @@ -11899,7 +27180,7 @@ "name": "GPT-5.2 Pro", "provider": "openai", "family": "gpt-pro", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -11916,7 +27197,6 @@ "function_calling", "reasoning", "vision", - "streaming", "structured_output" ], "pricing": { @@ -11950,27 +27230,21 @@ }, { "id": "gpt-5.2-pro-2025-12-11", - "name": "GPT-5.2 Pro 20251211", + "name": "gpt-5.2-pro-2025-12-11", "provider": "openai", - "family": "gpt5", - "created_at": "2025-12-10 10:49:19 +0530", + "family": null, + "created_at": "2025-12-10 05:19:19 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -11978,7 +27252,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -11992,7 +27266,7 @@ "name": "GPT-5.3 Chat (latest)", "provider": "openai", "family": "gpt", - "created_at": "2026-03-03 00:00:00 +0530", + "created_at": "2026-03-03 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": "2025-08-31", @@ -12009,7 +27283,6 @@ "function_calling", "structured_output", "vision", - "streaming", "reasoning" ], "pricing": { @@ -12017,7 +27290,7 @@ "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, @@ -12047,7 +27320,7 @@ "name": "GPT-5.3 Codex", "provider": "openai", "family": "gpt-codex", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -12065,15 +27338,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, @@ -12104,7 +27376,7 @@ "name": "GPT-5.3 Codex Spark", "provider": "openai", "family": "gpt-codex-spark", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-08-31", @@ -12129,7 +27401,7 @@ "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, @@ -12158,7 +27430,7 @@ "name": "GPT-5.4", "provider": "openai", "family": "gpt", - "created_at": "2026-03-05 00:00:00 +0530", + "created_at": "2026-03-05 00:00:00 UTC", "context_window": 1050000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -12176,15 +27448,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2.5, "output_per_million": 15, - "cached_input_per_million": 0.25 + "cache_read_input_per_million": 0.25 } } }, @@ -12217,27 +27488,21 @@ }, { "id": "gpt-5.4-2026-03-05", - "name": "GPT-5.4 20260305", + "name": "gpt-5.4-2026-03-05", "provider": "openai", - "family": "gpt5", - "created_at": "2026-03-05 01:24:22 +0530", + "family": null, + "created_at": "2026-03-04 19:54:22 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -12245,7 +27510,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, @@ -12259,7 +27524,7 @@ "name": "GPT-5.4 mini", "provider": "openai", "family": "gpt-mini", - "created_at": "2026-03-17 00:00:00 +0530", + "created_at": "2026-03-17 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -12276,15 +27541,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.75, "output_per_million": 4.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075 } } }, @@ -12312,35 +27576,29 @@ }, { "id": "gpt-5.4-mini-2026-03-17", - "name": "GPT-5.4 Mini 20260317", + "name": "gpt-5.4-mini-2026-03-17", "provider": "openai", - "family": "gpt5", - "created_at": "2026-03-14 06:47:56 +0530", + "family": null, + "created_at": "2026-03-14 01:17:56 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 1.25, - "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "input_per_million": 0.25, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.025 } } }, @@ -12354,7 +27612,7 @@ "name": "GPT-5.4 nano", "provider": "openai", "family": "gpt-nano", - "created_at": "2026-03-17 00:00:00 +0530", + "created_at": "2026-03-17 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -12371,15 +27629,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.2, "output_per_million": 1.25, - "cached_input_per_million": 0.02 + "cache_read_input_per_million": 0.02 } } }, @@ -12407,35 +27664,29 @@ }, { "id": "gpt-5.4-nano-2026-03-17", - "name": "GPT-5.4 Nano 20260317", + "name": "gpt-5.4-nano-2026-03-17", "provider": "openai", - "family": "gpt5", - "created_at": "2026-03-14 06:43:57 +0530", + "family": null, + "created_at": "2026-03-14 01:13:57 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 1.25, - "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "input_per_million": 0.05, + "output_per_million": 0.4, + "cache_read_input_per_million": 0.005 } } }, @@ -12449,7 +27700,7 @@ "name": "GPT-5.4 Pro", "provider": "openai", "family": "gpt-pro", - "created_at": "2026-03-05 00:00:00 +0530", + "created_at": "2026-03-05 00:00:00 UTC", "context_window": 1050000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -12466,7 +27717,6 @@ "function_calling", "reasoning", "vision", - "streaming", "structured_output" ], "pricing": { @@ -12504,13 +27754,46 @@ }, { "id": "gpt-5.4-pro-2026-03-05", - "name": "GPT-5.4 Pro 20260305", + "name": "gpt-5.4-pro-2026-03-05", "provider": "openai", - "family": "gpt5", - "created_at": "2026-03-05 02:57:37 +0530", + "family": null, + "created_at": "2026-03-04 21:27:37 UTC", "context_window": 128000, "max_output_tokens": 400000, "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system" + } + }, + { + "id": "gpt-5.5", + "name": "GPT-5.5", + "provider": "openai", + "family": "gpt", + "created_at": "2026-04-23 00:00:00 UTC", + "context_window": 1050000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2025-12-01", "modalities": { "input": [ "text", @@ -12522,9 +27805,64 @@ ] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 30, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system", + "source": "models.dev", + "provider_id": "openai", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-23", + "cost": { + "input": 5, + "output": 30, + "cache_read": 0.5, + "context_over_200k": { + "input": 10, + "output": 45, + "cache_read": 1 + } + }, + "limit": { + "context": 1050000, + "input": 922000, + "output": 128000 + }, + "knowledge": "2025-12-01" + } + }, + { + "id": "gpt-5.5-2026-04-23", + "name": "gpt-5.5-2026-04-23", + "provider": "openai", + "family": null, + "created_at": "2026-04-22 06:27:21 UTC", + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", "reasoning" ], "pricing": { @@ -12532,7 +27870,98 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10.0, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system" + } + }, + { + "id": "gpt-5.5-pro", + "name": "GPT-5.5 Pro", + "provider": "openai", + "family": "gpt-pro", + "created_at": "2026-04-23 00:00:00 UTC", + "context_window": 1050000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2025-12-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 30, + "output_per_million": 180 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system", + "source": "models.dev", + "provider_id": "openai", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-23", + "cost": { + "input": 30, + "output": 180, + "context_over_200k": { + "input": 60, + "output": 270 + } + }, + "limit": { + "context": 1050000, + "input": 922000, + "output": 128000 + }, + "knowledge": "2025-12-01" + } + }, + { + "id": "gpt-5.5-pro-2026-04-23", + "name": "gpt-5.5-pro-2026-04-23", + "provider": "openai", + "family": null, + "created_at": "2026-04-22 21:47:50 UTC", + "context_window": 128000, + "max_output_tokens": 400000, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125 } } }, @@ -12543,26 +27972,18 @@ }, { "id": "gpt-audio", - "name": "GPT-Audio", + "name": "gpt-audio", "provider": "openai", - "family": "other", - "created_at": "2025-08-28 05:30:49 +0530", + "family": null, + "created_at": "2025-08-28 00:00:49 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12578,26 +27999,18 @@ }, { "id": "gpt-audio-1.5", - "name": "GPT-Audio 1.5", + "name": "gpt-audio-1.5", "provider": "openai", - "family": "other", - "created_at": "2026-02-20 06:58:05 +0530", + "family": null, + "created_at": "2026-02-20 01:28:05 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12613,26 +28026,18 @@ }, { "id": "gpt-audio-2025-08-28", - "name": "GPT-Audio 20250828", + "name": "gpt-audio-2025-08-28", "provider": "openai", - "family": "other", - "created_at": "2025-08-27 06:25:46 +0530", + "family": null, + "created_at": "2025-08-27 00:55:46 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12648,26 +28053,18 @@ }, { "id": "gpt-audio-mini", - "name": "GPT-Audio Mini", + "name": "gpt-audio-mini", "provider": "openai", - "family": "other", - "created_at": "2025-10-03 22:50:27 +0530", + "family": null, + "created_at": "2025-10-03 17:20:27 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12683,26 +28080,18 @@ }, { "id": "gpt-audio-mini-2025-10-06", - "name": "GPT-Audio Mini 20251006", + "name": "gpt-audio-mini-2025-10-06", "provider": "openai", - "family": "other", - "created_at": "2025-10-03 22:52:17 +0530", + "family": null, + "created_at": "2025-10-03 17:22:17 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12718,26 +28107,18 @@ }, { "id": "gpt-audio-mini-2025-12-15", - "name": "GPT-Audio Mini 20251215", + "name": "gpt-audio-mini-2025-12-15", "provider": "openai", - "family": "other", - "created_at": "2025-12-15 06:23:28 +0530", + "family": null, + "created_at": "2025-12-15 00:53:28 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12756,7 +28137,7 @@ "name": "gpt-image-1", "provider": "openai", "family": "gpt-image", - "created_at": "2025-04-24 00:00:00 +0530", + "created_at": "2025-04-24 00:00:00 UTC", "context_window": 0, "max_output_tokens": 0, "knowledge_cutoff": null, @@ -12770,10 +28151,23 @@ ] }, "capabilities": [ - "vision", - "streaming" + "vision" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "cache_read_input_per_million": 1.25 + } + }, + "images": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 40.0, + "cache_read_input_per_million": 2.5 + } + } + }, "metadata": { "object": "model", "owned_by": "system", @@ -12795,7 +28189,7 @@ "name": "gpt-image-1-mini", "provider": "openai", "family": "gpt-image", - "created_at": "2025-09-26 00:00:00 +0530", + "created_at": "2025-09-26 00:00:00 UTC", "context_window": 0, "max_output_tokens": 0, "knowledge_cutoff": null, @@ -12810,10 +28204,23 @@ ] }, "capabilities": [ - "vision", - "streaming" + "vision" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "cache_read_input_per_million": 0.2 + } + }, + "images": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.25 + } + } + }, "metadata": { "object": "model", "owned_by": "system", @@ -12835,7 +28242,7 @@ "name": "gpt-image-1.5", "provider": "openai", "family": "gpt-image", - "created_at": "2025-11-25 00:00:00 +0530", + "created_at": "2025-11-25 00:00:00 UTC", "context_window": 0, "max_output_tokens": 0, "knowledge_cutoff": null, @@ -12850,10 +28257,23 @@ ] }, "capabilities": [ - "vision", - "streaming" + "vision" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "cache_read_input_per_million": 1.25 + } + }, + "images": { + "standard": { + "input_per_million": 8.0, + "output_per_million": 32.0, + "cache_read_input_per_million": 2.0 + } + } + }, "metadata": { "object": "model", "owned_by": "system", @@ -12871,25 +28291,73 @@ } }, { - "id": "gpt-realtime", - "name": "GPT-Realtime", + "id": "gpt-image-2", + "name": "gpt-image-2", "provider": "openai", - "family": "other", - "created_at": "2025-08-27 10:45:01 +0530", + "family": null, + "created_at": "2026-04-17 04:23:15 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system" + } + }, + { + "id": "gpt-image-2-2026-04-21", + "name": "gpt-image-2-2026-04-21", + "provider": "openai", + "family": null, + "created_at": "2026-04-17 04:26:34 UTC", + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "object": "model", + "owned_by": "system" + } + }, + { + "id": "gpt-realtime", + "name": "gpt-realtime", + "provider": "openai", + "family": null, + "created_at": "2025-08-27 05:15:01 UTC", + "context_window": 4096, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12905,24 +28373,18 @@ }, { "id": "gpt-realtime-1.5", - "name": "GPT-Realtime 1.5", + "name": "gpt-realtime-1.5", "provider": "openai", - "family": "other", - "created_at": "2026-02-19 06:07:49 +0530", + "family": null, + "created_at": "2026-02-19 00:37:49 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12938,24 +28400,18 @@ }, { "id": "gpt-realtime-2025-08-28", - "name": "GPT-Realtime 20250828", + "name": "gpt-realtime-2025-08-28", "provider": "openai", - "family": "other", - "created_at": "2025-08-27 10:46:13 +0530", + "family": null, + "created_at": "2025-08-27 05:16:13 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -12971,24 +28427,18 @@ }, { "id": "gpt-realtime-mini", - "name": "GPT-Realtime Mini", + "name": "gpt-realtime-mini", "provider": "openai", - "family": "other", - "created_at": "2025-10-04 00:15:33 +0530", + "family": null, + "created_at": "2025-10-03 18:45:33 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -13004,24 +28454,18 @@ }, { "id": "gpt-realtime-mini-2025-10-06", - "name": "GPT-Realtime Mini 20251006", + "name": "gpt-realtime-mini-2025-10-06", "provider": "openai", - "family": "other", - "created_at": "2025-10-04 00:16:15 +0530", + "family": null, + "created_at": "2025-10-03 18:46:15 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -13037,24 +28481,18 @@ }, { "id": "gpt-realtime-mini-2025-12-15", - "name": "GPT-Realtime Mini 20251215", + "name": "gpt-realtime-mini-2025-12-15", "provider": "openai", - "family": "other", - "created_at": "2025-12-13 13:16:47 +0530", + "family": null, + "created_at": "2025-12-13 07:46:47 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -13073,7 +28511,7 @@ "name": "o1", "provider": "openai", "family": "o", - "created_at": "2024-12-05 00:00:00 +0530", + "created_at": "2024-12-05 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13091,15 +28529,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 15, "output_per_million": 60, - "cached_input_per_million": 7.5 + "cache_read_input_per_million": 7.5 } } }, @@ -13126,27 +28563,21 @@ }, { "id": "o1-2024-12-17", - "name": "O1-20241217", + "name": "o1-2024-12-17", "provider": "openai", - "family": "o1", - "created_at": "2024-12-16 10:59:36 +0530", + "family": null, + "created_at": "2024-12-16 05:29:36 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -13167,7 +28598,7 @@ "name": "o1-mini", "provider": "openai", "family": "o-mini", - "created_at": "2024-09-12 00:00:00 +0530", + "created_at": "2024-09-12 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -13188,7 +28619,7 @@ "standard": { "input_per_million": 1.1, "output_per_million": 4.4, - "cached_input_per_million": 0.55 + "cache_read_input_per_million": 0.55 } } }, @@ -13216,7 +28647,7 @@ "name": "o1-preview", "provider": "openai", "family": "o", - "created_at": "2024-09-12 00:00:00 +0530", + "created_at": "2024-09-12 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -13236,7 +28667,7 @@ "standard": { "input_per_million": 15, "output_per_million": 60, - "cached_input_per_million": 7.5 + "cache_read_input_per_million": 7.5 } } }, @@ -13264,7 +28695,7 @@ "name": "o1-pro", "provider": "openai", "family": "o-pro", - "created_at": "2025-03-19 00:00:00 +0530", + "created_at": "2025-03-19 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13281,8 +28712,7 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -13314,27 +28744,21 @@ }, { "id": "o1-pro-2025-03-19", - "name": "O1-Pro 20250319", + "name": "o1-pro-2025-03-19", "provider": "openai", - "family": "o1_pro", - "created_at": "2025-03-18 04:15:04 +0530", + "family": null, + "created_at": "2025-03-17 22:45:04 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", + "vision", "reasoning" ], "pricing": { @@ -13355,7 +28779,7 @@ "name": "o3", "provider": "openai", "family": "o", - "created_at": "2025-04-16 00:00:00 +0530", + "created_at": "2025-04-16 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13373,15 +28797,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2, "output_per_million": 8, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5 } } }, @@ -13408,23 +28831,18 @@ }, { "id": "o3-2025-04-16", - "name": "O3-20250416", + "name": "o3-2025-04-16", "provider": "openai", - "family": "other", - "created_at": "2025-04-08 22:58:21 +0530", + "family": null, + "created_at": "2025-04-08 17:28:21 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "reasoning" ], "pricing": { @@ -13445,7 +28863,7 @@ "name": "o3-deep-research", "provider": "openai", "family": "o", - "created_at": "2024-06-26 00:00:00 +0530", + "created_at": "2024-06-26 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13461,15 +28879,14 @@ "capabilities": [ "function_calling", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 10, "output_per_million": 40, - "cached_input_per_million": 2.5 + "cache_read_input_per_million": 2.5 } } }, @@ -13496,23 +28913,18 @@ }, { "id": "o3-deep-research-2025-06-26", - "name": "O3-Deep Research 20250626", + "name": "o3-deep-research-2025-06-26", "provider": "openai", - "family": "other", - "created_at": "2025-06-25 20:56:59 +0530", + "family": null, + "created_at": "2025-06-25 15:26:59 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "reasoning" ], "pricing": { @@ -13533,7 +28945,7 @@ "name": "o3-mini", "provider": "openai", "family": "o-mini", - "created_at": "2024-12-20 00:00:00 +0530", + "created_at": "2024-12-20 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13548,15 +28960,14 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning", - "streaming" + "reasoning" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.1, "output_per_million": 4.4, - "cached_input_per_million": 0.55 + "cache_read_input_per_million": 0.55 } } }, @@ -13583,23 +28994,18 @@ }, { "id": "o3-mini-2025-01-31", - "name": "O3-Mini 20250131", + "name": "o3-mini-2025-01-31", "provider": "openai", - "family": "o3_mini", - "created_at": "2025-01-28 02:06:40 +0530", + "family": null, + "created_at": "2025-01-27 20:36:40 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "function_calling", "structured_output", "reasoning" @@ -13622,7 +29028,7 @@ "name": "o3-pro", "provider": "openai", "family": "o-pro", - "created_at": "2025-06-10 00:00:00 +0530", + "created_at": "2025-06-10 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13639,8 +29045,7 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { @@ -13672,23 +29077,18 @@ }, { "id": "o3-pro-2025-06-10", - "name": "O3-Pro 20250610", + "name": "o3-pro-2025-06-10", "provider": "openai", - "family": "other", - "created_at": "2025-06-06 05:09:21 +0530", + "family": null, + "created_at": "2025-06-05 23:39:21 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "reasoning" ], "pricing": { @@ -13709,7 +29109,7 @@ "name": "o4-mini", "provider": "openai", "family": "o-mini", - "created_at": "2025-04-16 00:00:00 +0530", + "created_at": "2025-04-16 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13726,15 +29126,14 @@ "function_calling", "structured_output", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.1, "output_per_million": 4.4, - "cached_input_per_million": 0.28 + "cache_read_input_per_million": 0.28 } } }, @@ -13761,23 +29160,18 @@ }, { "id": "o4-mini-2025-04-16", - "name": "O4 Mini 20250416", + "name": "o4-mini-2025-04-16", "provider": "openai", - "family": "other", - "created_at": "2025-04-08 23:01:46 +0530", + "family": null, + "created_at": "2025-04-08 17:31:46 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "reasoning" ], "pricing": { @@ -13798,7 +29192,7 @@ "name": "o4-mini-deep-research", "provider": "openai", "family": "o-mini", - "created_at": "2024-06-26 00:00:00 +0530", + "created_at": "2024-06-26 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -13814,15 +29208,14 @@ "capabilities": [ "function_calling", "reasoning", - "vision", - "streaming" + "vision" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2, "output_per_million": 8, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5 } } }, @@ -13849,23 +29242,18 @@ }, { "id": "o4-mini-deep-research-2025-06-26", - "name": "O4 Mini Deep Research 20250626", + "name": "o4-mini-deep-research-2025-06-26", "provider": "openai", - "family": "other", - "created_at": "2025-06-25 21:12:01 +0530", + "family": null, + "created_at": "2025-06-25 15:42:01 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, "capabilities": [ - "streaming", "reasoning" ], "pricing": { @@ -13883,25 +29271,20 @@ }, { "id": "omni-moderation-2024-09-26", - "name": "Omni Moderation 20240926", + "name": "omni-moderation-2024-09-26", "provider": "openai", - "family": "moderation", - "created_at": "2024-11-28 00:37:46 +0530", + "family": null, + "created_at": "2024-11-27 19:07:46 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text", - "moderation" - ] + "input": [], + "output": [] }, - "capabilities": [], + "capabilities": [ + "vision" + ], "pricing": {}, "metadata": { "object": "model", @@ -13910,25 +29293,20 @@ }, { "id": "omni-moderation-latest", - "name": "Omni Moderation Latest", + "name": "omni-moderation-latest", "provider": "openai", - "family": "moderation", - "created_at": "2024-11-15 22:17:45 +0530", + "family": null, + "created_at": "2024-11-15 16:47:45 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "image", - "pdf" - ], - "output": [ - "text", - "moderation" - ] + "input": [], + "output": [] }, - "capabilities": [], + "capabilities": [ + "vision" + ], "pricing": {}, "metadata": { "object": "model", @@ -13937,24 +29315,18 @@ }, { "id": "sora-2", - "name": "Sora 2", + "name": "sora-2", "provider": "openai", - "family": "other", - "created_at": "2025-10-06 05:26:55 +0530", + "family": null, + "created_at": "2025-10-05 23:56:55 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -13970,24 +29342,18 @@ }, { "id": "sora-2-pro", - "name": "Sora 2 Pro", + "name": "sora-2-pro", "provider": "openai", - "family": "other", - "created_at": "2025-10-06 05:27:43 +0530", + "family": null, + "created_at": "2025-10-05 23:57:43 UTC", "context_window": 4096, "max_output_tokens": 16384, "knowledge_cutoff": null, "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14006,7 +29372,7 @@ "name": "text-embedding-3-large", "provider": "openai", "family": "text-embedding", - "created_at": "2024-01-25 00:00:00 +0530", + "created_at": "2024-01-25 00:00:00 UTC", "context_window": 8191, "max_output_tokens": 3072, "knowledge_cutoff": null, @@ -14015,12 +29381,10 @@ "text" ], "output": [ - "text" + "embeddings" ] }, - "capabilities": [ - "batch" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14053,7 +29417,7 @@ "name": "text-embedding-3-small", "provider": "openai", "family": "text-embedding", - "created_at": "2024-01-25 00:00:00 +0530", + "created_at": "2024-01-25 00:00:00 UTC", "context_window": 8191, "max_output_tokens": 1536, "knowledge_cutoff": null, @@ -14062,12 +29426,10 @@ "text" ], "output": [ - "text" + "embeddings" ] }, - "capabilities": [ - "batch" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14100,7 +29462,7 @@ "name": "text-embedding-ada-002", "provider": "openai", "family": "text-embedding", - "created_at": "2022-12-15 00:00:00 +0530", + "created_at": "2022-12-15 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 1536, "knowledge_cutoff": null, @@ -14109,12 +29471,10 @@ "text" ], "output": [ - "text" + "embeddings" ] }, - "capabilities": [ - "batch" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14144,26 +29504,18 @@ }, { "id": "tts-1", - "name": "TTS-1", + "name": "tts-1", "provider": "openai", - "family": "tts1", - "created_at": "2023-04-20 03:19:11 +0530", + "family": null, + "created_at": "2023-04-19 21:49:11 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14179,26 +29531,18 @@ }, { "id": "tts-1-1106", - "name": "TTS-1 1106", + "name": "tts-1-1106", "provider": "openai", - "family": "tts1", - "created_at": "2023-11-04 04:44:01 +0530", + "family": null, + "created_at": "2023-11-03 23:14:01 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14214,26 +29558,18 @@ }, { "id": "tts-1-hd", - "name": "TTS-1 HD", + "name": "tts-1-hd", "provider": "openai", - "family": "tts1_hd", - "created_at": "2023-11-04 02:43:35 +0530", + "family": null, + "created_at": "2023-11-03 21:13:35 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14249,26 +29585,18 @@ }, { "id": "tts-1-hd-1106", - "name": "TTS-1 HD 1106", + "name": "tts-1-hd-1106", "provider": "openai", - "family": "tts1_hd", - "created_at": "2023-11-04 04:48:53 +0530", + "family": null, + "created_at": "2023-11-03 23:18:53 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text", - "audio" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14284,25 +29612,18 @@ }, { "id": "whisper-1", - "name": "Whisper 1", + "name": "whisper-1", "provider": "openai", - "family": "whisper", - "created_at": "2023-02-28 02:43:04 +0530", + "family": null, + "created_at": "2023-02-27 21:13:04 UTC", "context_window": null, "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { - "input": [ - "text", - "audio" - ], - "output": [ - "text" - ] + "input": [], + "output": [] }, - "capabilities": [ - "streaming" - ], + "capabilities": [], "pricing": { "text_tokens": { "standard": { @@ -14316,12 +29637,1068 @@ "owned_by": "openai-internal" } }, + { + "id": "ai21/jamba-large-1.7", + "name": "AI21: Jamba Large 1.7", + "provider": "openrouter", + "family": "ai21", + "created_at": "2025-08-08 16:03:40 UTC", + "context_window": 256000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0 + } + } + }, + "metadata": { + "description": "Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "aion-labs/aion-1.0", + "name": "AionLabs: Aion-1.0", + "provider": "openrouter", + "family": "aion-labs", + "created_at": "2025-02-04 19:32:37 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 4.0, + "output_per_million": 8.0 + } + } + }, + "metadata": { + "description": "Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "top_p" + ] + } + }, + { + "id": "aion-labs/aion-1.0-mini", + "name": "AionLabs: Aion-1.0-Mini", + "provider": "openrouter", + "family": "aion-labs", + "created_at": "2025-02-04 19:25:07 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7, + "output_per_million": 1.4 + } + } + }, + "metadata": { + "description": "Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "top_p" + ] + } + }, + { + "id": "aion-labs/aion-2.0", + "name": "AionLabs: Aion-2.0", + "provider": "openrouter", + "family": "aion-labs", + "created_at": "2026-02-23 21:15:06 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7999999999999999, + "output_per_million": 1.5999999999999999, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "top_p" + ] + } + }, + { + "id": "aion-labs/aion-rp-llama-3.1-8b", + "name": "AionLabs: Aion-RP 1.0 (8B)", + "provider": "openrouter", + "family": "aion-labs", + "created_at": "2025-02-04 19:18:38 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7999999999999999, + "output_per_million": 1.5999999999999999 + } + } + }, + "metadata": { + "description": "Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "temperature", + "top_p" + ] + } + }, + { + "id": "alfredpros/codellama-7b-instruct-solidity", + "name": "AlfredPros: CodeLLaMa 7B Instruct Solidity", + "provider": "openrouter", + "family": "alfredpros", + "created_at": "2025-04-14 14:44:34 UTC", + "context_window": 4096, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7999999999999999, + "output_per_million": 1.2 + } + } + }, + "metadata": { + "description": "A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": "alpaca" + }, + "top_provider": { + "context_length": 4096, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "alibaba/tongyi-deepresearch-30b-a3b", + "name": "Tongyi DeepResearch 30B A3B", + "provider": "openrouter", + "family": "alibaba", + "created_at": "2025-09-18 15:53:24 UTC", + "context_window": 131072, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09, + "output_per_million": 0.44999999999999996, + "cache_read_input_per_million": 0.09 + } + } + }, + "metadata": { + "description": "Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "allenai/olmo-3-32b-think", + "name": "AllenAI: Olmo 3 32B Think", + "provider": "openrouter", + "family": "allenai", + "created_at": "2025-11-21 20:51:16 UTC", + "context_window": 65536, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.5 + } + } + }, + "metadata": { + "description": "Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "allenai/olmo-3.1-32b-instruct", + "name": "AllenAI: Olmo 3.1 32B Instruct", + "provider": "openrouter", + "family": "allenai", + "created_at": "2026-01-06 19:42:34 UTC", + "context_window": 65536, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.19999999999999998, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "description": "Olmo 3.1 32B Instruct is a large-scale, 32-billion-parameter instruction-tuned language model engineered for high-performance conversational AI, multi-turn dialogue, and practical instruction following. As part of the Olmo 3.1 family, this...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "alpindale/goliath-120b", + "name": "Goliath 120B", + "provider": "openrouter", + "family": "alpindale", + "created_at": "2023-11-10 00:00:00 UTC", + "context_window": 6144, + "max_output_tokens": 1024, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.75, + "output_per_million": 7.5 + } + } + }, + "metadata": { + "description": "A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama2", + "instruct_type": "airoboros" + }, + "top_provider": { + "context_length": 6144, + "max_completion_tokens": 1024, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "amazon/nova-2-lite-v1", + "name": "Amazon: Nova 2 Lite", + "provider": "openrouter", + "family": "amazon", + "created_at": "2025-12-02 17:31:12 UTC", + "context_window": 1000000, + "max_output_tokens": 65535, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 2.5 + } + } + }, + "metadata": { + "description": "Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...", + "architecture": { + "modality": "text+image+file+video->text", + "input_modalities": [ + "text", + "image", + "video", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Nova", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65535, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "amazon/nova-lite-v1", + "name": "Amazon: Nova Lite 1.0", + "provider": "openrouter", + "family": "amazon", + "created_at": "2024-12-05 22:22:43 UTC", + "context_window": 300000, + "max_output_tokens": 5120, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.06, + "output_per_million": 0.24 + } + } + }, + "metadata": { + "description": "Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Nova", + "instruct_type": null + }, + "top_provider": { + "context_length": 300000, + "max_completion_tokens": 5120, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "amazon/nova-micro-v1", + "name": "Amazon: Nova Micro 1.0", + "provider": "openrouter", + "family": "amazon", + "created_at": "2024-12-05 22:20:37 UTC", + "context_window": 128000, + "max_output_tokens": 5120, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.035, + "output_per_million": 0.14 + } + } + }, + "metadata": { + "description": "Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Nova", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 5120, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "amazon/nova-premier-v1", + "name": "Amazon: Nova Premier 1.0", + "provider": "openrouter", + "family": "amazon", + "created_at": "2025-10-31 22:38:52 UTC", + "context_window": 1000000, + "max_output_tokens": 32000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 12.5, + "cache_read_input_per_million": 0.625 + } + } + }, + "metadata": { + "description": "Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Nova", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "amazon/nova-pro-v1", + "name": "Amazon: Nova Pro 1.0", + "provider": "openrouter", + "family": "amazon", + "created_at": "2024-12-05 22:05:03 UTC", + "context_window": 300000, + "max_output_tokens": 5120, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7999999999999999, + "output_per_million": 3.1999999999999997 + } + } + }, + "metadata": { + "description": "Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Nova", + "instruct_type": null + }, + "top_provider": { + "context_length": 300000, + "max_completion_tokens": 5120, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "anthracite-org/magnum-v4-72b", + "name": "Magnum v4 72B", + "provider": "openrouter", + "family": "anthracite-org", + "created_at": "2024-10-22 00:00:00 UTC", + "context_window": 16384, + "max_output_tokens": 2048, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 5.0 + } + } + }, + "metadata": { + "description": "This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 16384, + "max_completion_tokens": 2048, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "anthropic/claude-3-haiku", + "name": "Anthropic: Claude 3 Haiku", + "provider": "openrouter", + "family": "anthropic", + "created_at": "2024-03-13 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 1.25, + "cache_read_input_per_million": 0.03 + } + } + }, + "metadata": { + "description": "Claude 3 Haiku is Anthropic's fastest and most compact model for\nnear-instant responsiveness. Quick and accurate targeted performance.\n\nSee the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku)\n\n#multimodal", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "anthropic/claude-3.5-haiku", "name": "Claude Haiku 3.5", "provider": "openrouter", "family": "claude-haiku", - "created_at": "2024-10-22 00:00:00 +0530", + "created_at": "2024-10-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": "2024-07-31", @@ -14337,18 +30714,48 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.8, "output_per_million": 4, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08, + "cache_write_input_per_million": 1 } } }, "metadata": { + "description": "Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 8192, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14373,7 +30780,7 @@ "name": "Claude Sonnet 3.7", "provider": "openrouter", "family": "claude-sonnet", - "created_at": "2025-02-19 00:00:00 +0530", + "created_at": "2025-02-19 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -14390,18 +30797,50 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, "metadata": { + "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 64000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14421,12 +30860,77 @@ "knowledge": "2024-01" } }, + { + "id": "anthropic/claude-3.7-sonnet:thinking", + "name": "Anthropic: Claude 3.7 Sonnet (thinking)", + "provider": "openrouter", + "family": "anthropic", + "created_at": "2025-02-24 18:35:10 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 15.0, + "cache_read_input_per_million": 0.3 + } + } + }, + "metadata": { + "description": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 64000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "anthropic/claude-haiku-4.5", "name": "Claude Haiku 4.5", "provider": "openrouter", "family": "claude-haiku", - "created_at": "2025-10-15 00:00:00 +0530", + "created_at": "2025-10-15 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-02-28", @@ -14444,18 +30948,52 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1, "output_per_million": 5, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 } } }, "metadata": { + "description": "Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 64000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14480,7 +31018,7 @@ "name": "Claude Opus 4", "provider": "openrouter", "family": "claude-opus", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -14497,18 +31035,51 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, "metadata": { + "description": "Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 32000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14533,7 +31104,7 @@ "name": "Claude Opus 4.1", "provider": "openrouter", "family": "claude-opus", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-03-31", @@ -14551,18 +31122,53 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 15, "output_per_million": 75, - "cached_input_per_million": 1.5 + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 } } }, "metadata": { + "description": "Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 32000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14587,7 +31193,7 @@ "name": "Claude Opus 4.5", "provider": "openrouter", "family": "claude-opus", - "created_at": "2025-11-24 00:00:00 +0530", + "created_at": "2025-11-24 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 32000, "knowledge_cutoff": "2025-05-30", @@ -14605,18 +31211,53 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, "metadata": { + "description": "Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 64000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "verbosity" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14641,10 +31282,10 @@ "name": "Claude Opus 4.6", "provider": "openrouter", "family": "claude-opus", - "created_at": "2026-02-05 00:00:00 +0530", + "created_at": "2026-02-05 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": "2025-05-30", + "knowledge_cutoff": "2025-05-31", "modalities": { "input": [ "text", @@ -14659,18 +31300,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 5, "output_per_million": 25, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 } } }, "metadata": { + "description": "Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p", + "verbosity" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14693,7 +31370,166 @@ "context": 1000000, "output": 128000 }, - "knowledge": "2025-05-30" + "knowledge": "2025-05-31" + } + }, + { + "id": "anthropic/claude-opus-4.6-fast", + "name": "Anthropic: Claude Opus 4.6 (Fast)", + "provider": "openrouter", + "family": "anthropic", + "created_at": "2026-04-07 20:07:52 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 30.0, + "output_per_million": 150.0, + "cache_read_input_per_million": 3.0 + } + } + }, + "metadata": { + "description": "Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p", + "verbosity" + ] + } + }, + { + "id": "anthropic/claude-opus-4.7", + "name": "Claude Opus 4.7", + "provider": "openrouter", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "description": "Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25, + "context_over_200k": { + "input": 10, + "output": 37.5, + "cache_read": 1, + "cache_write": 12.5 + } + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" } }, { @@ -14701,7 +31537,7 @@ "name": "Claude Sonnet 4", "provider": "openrouter", "family": "claude-sonnet", - "created_at": "2025-05-22 00:00:00 +0530", + "created_at": "2025-05-22 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-03-31", @@ -14718,18 +31554,51 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { + "description": "Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 64000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14760,7 +31629,7 @@ "name": "Claude Sonnet 4.5", "provider": "openrouter", "family": "claude-sonnet", - "created_at": "2025-09-29 00:00:00 +0530", + "created_at": "2025-09-29 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 64000, "knowledge_cutoff": "2025-07-31", @@ -14778,18 +31647,53 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { + "description": "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 64000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14820,10 +31724,10 @@ "name": "Claude Sonnet 4.6", "provider": "openrouter", "family": "claude-sonnet", - "created_at": "2026-02-17 00:00:00 +0530", + "created_at": "2026-02-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 128000, - "knowledge_cutoff": null, + "knowledge_cutoff": "2025-08-31", "modalities": { "input": [ "text", @@ -14837,18 +31741,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.3 + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { + "description": "Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Claude", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p", + "verbosity" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -14870,7 +31810,256 @@ "limit": { "context": 1000000, "output": 128000 + }, + "knowledge": "2025-08-31" + } + }, + { + "id": "arcee-ai/coder-large", + "name": "Arcee AI: Coder Large", + "provider": "openrouter", + "family": "arcee-ai", + "created_at": "2025-05-05 20:57:43 UTC", + "context_window": 32768, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 0.7999999999999999 + } } + }, + "metadata": { + "description": "Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "arcee-ai/maestro-reasoning", + "name": "Arcee AI: Maestro Reasoning", + "provider": "openrouter", + "family": "arcee-ai", + "created_at": "2025-05-05 21:41:09 UTC", + "context_window": 131072, + "max_output_tokens": 32000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.8999999999999999, + "output_per_million": 3.3000000000000003 + } + } + }, + "metadata": { + "description": "Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "arcee-ai/spotlight", + "name": "Arcee AI: Spotlight", + "provider": "openrouter", + "family": "arcee-ai", + "created_at": "2025-05-05 21:45:52 UTC", + "context_window": 131072, + "max_output_tokens": 65537, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.18, + "output_per_million": 0.18 + } + } + }, + "metadata": { + "description": "Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 65537, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "arcee-ai/trinity-large-preview", + "name": "Arcee AI: Trinity Large Preview", + "provider": "openrouter", + "family": "arcee-ai", + "created_at": "2026-01-27 22:24:30 UTC", + "context_window": 131000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.44999999999999996 + } + } + }, + "metadata": { + "description": "Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "structured_outputs", + "temperature", + "tools", + "top_k", + "top_p" + ] } }, { @@ -14878,7 +32067,7 @@ "name": "Trinity Large Preview", "provider": "openrouter", "family": "trinity", - "created_at": "2026-01-28 00:00:00 +0530", + "created_at": "2026-01-28 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -14918,7 +32107,7 @@ "name": "Trinity Large Thinking", "provider": "openrouter", "family": "trinity", - "created_at": "2026-04-01 00:00:00 +0530", + "created_at": "2026-04-01 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 80000, "knowledge_cutoff": null, @@ -14932,7 +32121,10 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -14943,6 +32135,42 @@ } }, "metadata": { + "description": "Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -14959,12 +32187,563 @@ } } }, + { + "id": "arcee-ai/trinity-mini", + "name": "Arcee AI: Trinity Mini", + "provider": "openrouter", + "family": "arcee-ai", + "created_at": "2025-12-01 15:08:40 UTC", + "context_window": 131072, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.045, + "output_per_million": 0.15 + } + } + }, + "metadata": { + "description": "Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "arcee-ai/virtuoso-large", + "name": "Arcee AI: Virtuoso Large", + "provider": "openrouter", + "family": "arcee-ai", + "created_at": "2025-05-05 21:01:25 UTC", + "context_window": 131072, + "max_output_tokens": 64000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.75, + "output_per_million": 1.2 + } + } + }, + "metadata": { + "description": "Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 64000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "baidu/cobuddy:free", + "name": "Baidu Qianfan: CoBuddy (free)", + "provider": "openrouter", + "family": "baidu", + "created_at": "2026-05-06 02:44:40 UTC", + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "description": "CoBuddy is a code generation model from Baidu, optimized for coding tasks and AI Agent workflows. It features high inference throughput and low end-to-end latency, with native support for tool...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "stop", + "tools" + ] + } + }, + { + "id": "baidu/ernie-4.5-21b-a3b", + "name": "Baidu: ERNIE 4.5 21B A3B", + "provider": "openrouter", + "family": "baidu", + "created_at": "2025-08-12 21:29:27 UTC", + "context_window": 120000, + "max_output_tokens": 8000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.07, + "output_per_million": 0.28 + } + } + }, + "metadata": { + "description": "A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 120000, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "baidu/ernie-4.5-21b-a3b-thinking", + "name": "Baidu: ERNIE 4.5 21B A3B Thinking", + "provider": "openrouter", + "family": "baidu", + "created_at": "2025-10-09 22:28:07 UTC", + "context_window": 131072, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.07, + "output_per_million": 0.28 + } + } + }, + "metadata": { + "description": "ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "baidu/ernie-4.5-300b-a47b", + "name": "Baidu: ERNIE 4.5 300B A47B ", + "provider": "openrouter", + "family": "baidu", + "created_at": "2025-06-30 16:15:39 UTC", + "context_window": 123000, + "max_output_tokens": 12000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.28, + "output_per_million": 1.1 + } + } + }, + "metadata": { + "description": "ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 123000, + "max_completion_tokens": 12000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "baidu/ernie-4.5-vl-28b-a3b", + "name": "Baidu: ERNIE 4.5 VL 28B A3B", + "provider": "openrouter", + "family": "baidu", + "created_at": "2025-08-12 21:07:16 UTC", + "context_window": 30000, + "max_output_tokens": 8000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.14, + "output_per_million": 0.56 + } + } + }, + "metadata": { + "description": "A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing....", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 30000, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "baidu/ernie-4.5-vl-424b-a47b", + "name": "Baidu: ERNIE 4.5 VL 424B A47B ", + "provider": "openrouter", + "family": "baidu", + "created_at": "2025-06-30 16:28:23 UTC", + "context_window": 123000, + "max_output_tokens": 16000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.42, + "output_per_million": 1.25 + } + } + }, + "metadata": { + "description": "ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 123000, + "max_completion_tokens": 16000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "baidu/qianfan-ocr-fast:free", + "name": "Baidu: Qianfan-OCR-Fast (free)", + "provider": "openrouter", + "family": "baidu", + "created_at": "2026-04-20 17:51:12 UTC", + "context_window": 65536, + "max_output_tokens": 28672, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "description": "Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 28672, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_p" + ] + } + }, { "id": "black-forest-labs/flux.2-flex", "name": "FLUX.2 Flex", "provider": "openrouter", "family": "flux", - "created_at": "2025-11-25 00:00:00 +0530", + "created_at": "2025-11-25 00:00:00 UTC", "context_window": 67344, "max_output_tokens": 67344, "knowledge_cutoff": null, @@ -15004,7 +32783,7 @@ "name": "FLUX.2 Klein 4B", "provider": "openrouter", "family": "flux", - "created_at": "2026-01-14 00:00:00 +0530", + "created_at": "2026-01-14 00:00:00 UTC", "context_window": 40960, "max_output_tokens": 40960, "knowledge_cutoff": null, @@ -15044,7 +32823,7 @@ "name": "FLUX.2 Max", "provider": "openrouter", "family": "flux", - "created_at": "2025-12-16 00:00:00 +0530", + "created_at": "2025-12-16 00:00:00 UTC", "context_window": 46864, "max_output_tokens": 46864, "knowledge_cutoff": null, @@ -15084,7 +32863,7 @@ "name": "FLUX.2 Pro", "provider": "openrouter", "family": "flux", - "created_at": "2025-11-25 00:00:00 +0530", + "created_at": "2025-11-25 00:00:00 UTC", "context_window": 46864, "max_output_tokens": 46864, "knowledge_cutoff": null, @@ -15119,12 +32898,284 @@ "knowledge": "2025-06" } }, + { + "id": "bytedance-seed/seed-1.6", + "name": "ByteDance Seed: Seed 1.6", + "provider": "openrouter", + "family": "bytedance-seed", + "created_at": "2025-12-23 15:49:57 UTC", + "context_window": 262144, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0 + } + } + }, + "metadata": { + "description": "Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "bytedance-seed/seed-1.6-flash", + "name": "ByteDance Seed: Seed 1.6 Flash", + "provider": "openrouter", + "family": "bytedance-seed", + "created_at": "2025-12-23 15:50:11 UTC", + "context_window": 262144, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "description": "Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "bytedance-seed/seed-2.0-lite", + "name": "ByteDance Seed: Seed-2.0-Lite", + "provider": "openrouter", + "family": "bytedance-seed", + "created_at": "2026-03-10 15:40:31 UTC", + "context_window": 262144, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 2.0 + } + } + }, + "metadata": { + "description": "Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "bytedance-seed/seed-2.0-mini", + "name": "ByteDance Seed: Seed-2.0-Mini", + "provider": "openrouter", + "family": "bytedance-seed", + "created_at": "2026-02-26 18:38:27 UTC", + "context_window": 262144, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.39999999999999997 + } + } + }, + "metadata": { + "description": "Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "bytedance-seed/seedream-4.5", "name": "Seedream 4.5", "provider": "openrouter", "family": "seed", - "created_at": "2025-12-23 00:00:00 +0530", + "created_at": "2025-12-23 00:00:00 UTC", "context_window": 4096, "max_output_tokens": 4096, "knowledge_cutoff": null, @@ -15159,12 +33210,77 @@ "knowledge": "2025-06" } }, + { + "id": "bytedance/ui-tars-1.5-7b", + "name": "ByteDance: UI-TARS 7B ", + "provider": "openrouter", + "family": "bytedance", + "created_at": "2025-07-22 17:24:16 UTC", + "context_window": 128000, + "max_output_tokens": 2048, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.19999999999999998, + "cache_read_input_per_million": 0.09999999999999999 + } + } + }, + "metadata": { + "description": "UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 2048, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "name": "Uncensored (free)", "provider": "openrouter", "family": "mistral", - "created_at": "2025-07-09 00:00:00 +0530", + "created_at": "2025-07-09 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -15177,10 +33293,40 @@ ] }, "capabilities": [ - "structured_output" + "structured_output", + "streaming" ], "pricing": {}, "metadata": { + "description": "Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15198,12 +33344,402 @@ "knowledge": "2025-06" } }, + { + "id": "cohere/command-a", + "name": "Cohere: Command A", + "provider": "openrouter", + "family": "cohere", + "created_at": "2025-03-13 19:32:22 UTC", + "context_window": 256000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 8192, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "cohere/command-r-08-2024", + "name": "Cohere: Command R (08-2024)", + "provider": "openrouter", + "family": "cohere", + "created_at": "2024-08-30 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "description": "command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Cohere", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "cohere/command-r-plus-08-2024", + "name": "Cohere: Command R+ (08-2024)", + "provider": "openrouter", + "family": "cohere", + "created_at": "2024-08-30 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Cohere", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "cohere/command-r7b-12-2024", + "name": "Cohere: Command R7B (12-2024)", + "provider": "openrouter", + "family": "cohere", + "created_at": "2024-12-14 06:35:52 UTC", + "context_window": 128000, + "max_output_tokens": 4000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.0375, + "output_per_million": 0.15 + } + } + }, + "metadata": { + "description": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Cohere", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "deepcogito/cogito-v2.1-671b", + "name": "Deep Cogito: Cogito v2.1 671B", + "provider": "openrouter", + "family": "deepcogito", + "created_at": "2025-11-13 22:00:33 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 1.25 + } + } + }, + "metadata": { + "description": "Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "deepseek/deepseek-chat", + "name": "DeepSeek: DeepSeek V3", + "provider": "openrouter", + "family": "deepseek", + "created_at": "2024-12-26 19:28:40 UTC", + "context_window": 163840, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.32, + "output_per_million": 0.8899999999999999 + } + } + }, + "metadata": { + "description": "DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "deepseek/deepseek-chat-v3-0324", "name": "DeepSeek V3 0324", "provider": "openrouter", "family": "deepseek", - "created_at": "2025-03-24 00:00:00 +0530", + "created_at": "2025-03-24 00:00:00 UTC", "context_window": 16384, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -15216,10 +33752,56 @@ ] }, "capabilities": [ - "structured_output" + "structured_output", + "streaming", + "function_calling", + "predicted_outputs" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.19999999999999998, + "output_per_million": 0.77, + "cache_read_input_per_million": 0.135 + } + } + }, "metadata": { + "description": "DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15242,7 +33824,7 @@ "name": "DeepSeek-V3.1", "provider": "openrouter", "family": "deepseek", - "created_at": "2025-08-21 00:00:00 +0530", + "created_at": "2025-08-21 00:00:00 UTC", "context_window": 163840, "max_output_tokens": 163840, "knowledge_cutoff": null, @@ -15257,7 +33839,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -15268,6 +33852,45 @@ } }, "metadata": { + "description": "DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-v3.1" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 7168, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15290,7 +33913,7 @@ "name": "DeepSeek: R1", "provider": "openrouter", "family": "deepseek-thinking", - "created_at": "2025-01-20 00:00:00 +0530", + "created_at": "2025-01-20 00:00:00 UTC", "context_window": 64000, "max_output_tokens": 16000, "knowledge_cutoff": null, @@ -15304,7 +33927,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -15315,6 +33939,40 @@ } }, "metadata": { + "description": "DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-r1" + }, + "top_provider": { + "context_length": 64000, + "max_completion_tokens": 16000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15332,12 +33990,84 @@ "knowledge": "2024-07" } }, + { + "id": "deepseek/deepseek-r1-0528", + "name": "DeepSeek: R1 0528", + "provider": "openrouter", + "family": "deepseek", + "created_at": "2025-05-28 17:59:30 UTC", + "context_window": 163840, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 2.1500000000000004, + "cache_read_input_per_million": 0.35 + } + } + }, + "metadata": { + "description": "May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-r1" + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "deepseek/deepseek-r1-distill-llama-70b", "name": "DeepSeek R1 Distill Llama 70B", "provider": "openrouter", "family": "deepseek-thinking", - "created_at": "2025-01-23 00:00:00 +0530", + "created_at": "2025-01-23 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -15351,10 +34081,53 @@ }, "capabilities": [ "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7, + "output_per_million": 0.7999999999999999 + } + } + }, "metadata": { + "description": "DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "deepseek-r1" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15372,12 +34145,78 @@ "knowledge": "2024-10" } }, + { + "id": "deepseek/deepseek-r1-distill-qwen-32b", + "name": "DeepSeek: R1 Distill Qwen 32B", + "provider": "openrouter", + "family": "deepseek", + "created_at": "2025-01-29 23:53:50 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.29, + "output_per_million": 0.29 + } + } + }, + "metadata": { + "description": "DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": "deepseek-r1" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_logprobs", + "top_p" + ] + } + }, { "id": "deepseek/deepseek-v3.1-terminus", "name": "DeepSeek V3.1 Terminus", "provider": "openrouter", "family": "deepseek", - "created_at": "2025-09-22 00:00:00 +0530", + "created_at": "2025-09-22 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15392,7 +34231,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -15403,6 +34244,43 @@ } }, "metadata": { + "description": "DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-v3.1" + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15425,7 +34303,7 @@ "name": "DeepSeek V3.1 Terminus (exacto)", "provider": "openrouter", "family": "deepseek", - "created_at": "2025-09-22 00:00:00 +0530", + "created_at": "2025-09-22 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15473,7 +34351,7 @@ "name": "DeepSeek V3.2", "provider": "openrouter", "family": "deepseek", - "created_at": "2025-12-01 00:00:00 +0530", + "created_at": "2025-12-01 00:00:00 UTC", "context_window": 163840, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15488,7 +34366,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -15499,6 +34379,43 @@ } }, "metadata": { + "description": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15516,12 +34433,83 @@ "knowledge": "2024-07" } }, + { + "id": "deepseek/deepseek-v3.2-exp", + "name": "DeepSeek: DeepSeek V3.2 Exp", + "provider": "openrouter", + "family": "deepseek", + "created_at": "2025-09-29 12:54:41 UTC", + "context_window": 163840, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.27, + "output_per_million": 0.41 + } + } + }, + "metadata": { + "description": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": "deepseek-v3.1" + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "deepseek/deepseek-v3.2-speciale", "name": "DeepSeek V3.2 Speciale", "provider": "openrouter", "family": "deepseek", - "created_at": "2025-12-01 00:00:00 +0530", + "created_at": "2025-12-01 00:00:00 UTC", "context_window": 163840, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15536,7 +34524,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -15547,6 +34537,41 @@ } }, "metadata": { + "description": "DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 163840, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -15564,12 +34589,268 @@ "knowledge": "2024-07" } }, + { + "id": "deepseek/deepseek-v4-flash", + "name": "DeepSeek V4 Flash", + "provider": "openrouter", + "family": "deepseek-flash", + "created_at": "2026-04-24 00:00:00 UTC", + "context_window": 1048576, + "max_output_tokens": 393216, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.14, + "output_per_million": 0.28, + "cache_read_input_per_million": 0.028 + } + } + }, + "metadata": { + "description": "DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 384000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-24", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 0.14, + "output": 0.28, + "cache_read": 0.028 + }, + "limit": { + "context": 1048576, + "output": 393216 + }, + "knowledge": "2025-05" + } + }, + { + "id": "deepseek/deepseek-v4-pro", + "name": "DeepSeek V4 Pro", + "provider": "openrouter", + "family": "deepseek-thinking", + "created_at": "2026-04-24 00:00:00 UTC", + "context_window": 1048576, + "max_output_tokens": 393216, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.74, + "output_per_million": 3.48, + "cache_read_input_per_million": 0.145 + } + } + }, + "metadata": { + "description": "DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 384000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-24", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 1.74, + "output": 3.48, + "cache_read": 0.145 + }, + "limit": { + "context": 1048576, + "output": 393216 + }, + "knowledge": "2025-05" + } + }, + { + "id": "essentialai/rnj-1-instruct", + "name": "EssentialAI: Rnj 1 Instruct", + "provider": "openrouter", + "family": "essentialai", + "created_at": "2025-12-07 08:07:27 UTC", + "context_window": 32768, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.15 + } + } + }, + "metadata": { + "description": "Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong performance...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "google/gemini-2.0-flash-001", "name": "Gemini 2.0 Flash", "provider": "openrouter", "family": "gemini-flash", - "created_at": "2024-12-11 00:00:00 +0530", + "created_at": "2024-12-11 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -15588,18 +34869,52 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "description": "Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -15618,12 +34933,83 @@ "knowledge": "2024-06" } }, + { + "id": "google/gemini-2.0-flash-lite-001", + "name": "Google: Gemini 2.0 Flash Lite", + "provider": "openrouter", + "family": "google", + "created_at": "2025-02-25 17:56:52 UTC", + "context_window": 1048576, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3, + "reasoning_output_per_million": 0.3 + } + } + }, + "metadata": { + "description": "Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5),...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "google/gemini-2.5-flash", "name": "Gemini 2.5 Flash", "provider": "openrouter", "family": "gemini-flash", - "created_at": "2025-07-17 00:00:00 +0530", + "created_at": "2025-07-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15643,18 +35029,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.0375 + "cache_read_input_per_million": 0.0375 } } }, "metadata": { + "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "file", + "image", + "text", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65535, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -15673,12 +35095,77 @@ "knowledge": "2025-01" } }, + { + "id": "google/gemini-2.5-flash-image", + "name": "Google: Nano Banana (Gemini 2.5 Flash Image)", + "provider": "openrouter", + "family": "google", + "created_at": "2025-10-07 20:53:51 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "image", + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 2.5, + "cache_read_input_per_million": 0.03, + "reasoning_output_per_million": 2.5 + } + } + }, + "metadata": { + "description": "Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...", + "architecture": { + "modality": "text+image->text+image", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "image", + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_p" + ] + } + }, { "id": "google/gemini-2.5-flash-lite", "name": "Gemini 2.5 Flash Lite", "provider": "openrouter", "family": "gemini-flash-lite", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15698,18 +35185,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65535, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -15733,7 +35256,7 @@ "name": "Gemini 2.5 Flash Lite Preview 09-25", "provider": "openrouter", "family": "gemini-flash-lite", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15753,18 +35276,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "description": "Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65535, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -15788,7 +35347,7 @@ "name": "Gemini 2.5 Flash Preview 09-25", "provider": "openrouter", "family": "gemini-flash", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15815,7 +35374,7 @@ "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.031 + "cache_read_input_per_million": 0.031 } } }, @@ -15843,7 +35402,7 @@ "name": "Gemini 2.5 Pro", "provider": "openrouter", "family": "gemini-pro", - "created_at": "2025-03-20 00:00:00 +0530", + "created_at": "2025-03-20 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15863,18 +35422,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -15884,7 +35479,12 @@ "cost": { "input": 1.25, "output": 10, - "cache_read": 0.31 + "cache_read": 0.125, + "context_over_200k": { + "input": 2.5, + "output": 15, + "cache_read": 0.25 + } }, "limit": { "context": 1048576, @@ -15893,12 +35493,84 @@ "knowledge": "2025-01" } }, + { + "id": "google/gemini-2.5-pro-preview", + "name": "Google: Gemini 2.5 Pro Preview 06-05", + "provider": "openrouter", + "family": "google", + "created_at": "2025-06-05 15:27:37 UTC", + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "file", + "image", + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 10.0, + "cache_read_input_per_million": 0.125, + "reasoning_output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "architecture": { + "modality": "text+image+file+audio->text", + "input_modalities": [ + "file", + "image", + "text", + "audio" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "google/gemini-2.5-pro-preview-05-06", "name": "Gemini 2.5 Pro Preview 05-06", "provider": "openrouter", "family": "gemini-pro", - "created_at": "2025-05-06 00:00:00 +0530", + "created_at": "2025-05-06 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15918,18 +35590,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.31 } } }, "metadata": { + "description": "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65535, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -15953,7 +35661,7 @@ "name": "Gemini 2.5 Pro Preview 06-05", "provider": "openrouter", "family": "gemini-pro", - "created_at": "2025-06-05 00:00:00 +0530", + "created_at": "2025-06-05 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -15980,7 +35688,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.31 } } }, @@ -16008,7 +35716,7 @@ "name": "Gemini 3 Flash Preview", "provider": "openrouter", "family": "gemini-flash", - "created_at": "2025-12-17 00:00:00 +0530", + "created_at": "2025-12-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -16028,18 +35736,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.5, "output_per_million": 3, - "cached_input_per_million": 0.05 + "cache_read_input_per_million": 0.05 } } }, "metadata": { + "description": "Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -16061,12 +35805,79 @@ "knowledge": "2025-01" } }, + { + "id": "google/gemini-3-pro-image-preview", + "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", + "provider": "openrouter", + "family": "google", + "created_at": "2025-11-20 15:49:57 UTC", + "context_window": 65536, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "image", + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 12.0, + "cache_read_input_per_million": 0.19999999999999998, + "reasoning_output_per_million": 12.0 + } + } + }, + "metadata": { + "description": "Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...", + "architecture": { + "modality": "text+image->text+image", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "image", + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_p" + ] + } + }, { "id": "google/gemini-3-pro-preview", "name": "Gemini 3 Pro Preview", "provider": "openrouter", "family": "gemini-pro", - "created_at": "2025-11-18 00:00:00 +0530", + "created_at": "2025-11-18 00:00:00 UTC", "context_window": 1050000, "max_output_tokens": 66000, "knowledge_cutoff": null, @@ -16117,12 +35928,94 @@ "knowledge": "2025-01" } }, + { + "id": "google/gemini-3.1-flash-image-preview", + "name": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", + "provider": "openrouter", + "family": "gemini-flash", + "created_at": "2026-02-26 00:00:00 UTC", + "context_window": 65536, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "image" + ] + }, + "capabilities": [ + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 3 + } + } + }, + "metadata": { + "description": "Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...", + "architecture": { + "modality": "text+image->text+image", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "image", + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-02-26", + "cost": { + "input": 0.5, + "output": 3 + }, + "limit": { + "context": 65536, + "output": 65536 + }, + "knowledge": "2025-01" + } + }, { "id": "google/gemini-3.1-flash-lite-preview", "name": "Gemini 3.1 Flash Lite Preview", "provider": "openrouter", "family": "gemini-flash-lite", - "created_at": "2026-03-03 00:00:00 +0530", + "created_at": "2026-03-03 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -16142,14 +36035,16 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.25, "output_per_million": 1.5, - "cached_input_per_million": 0.025, + "cache_read_input_per_million": 0.025, + "cache_write_input_per_million": 0.083, "reasoning_output_per_million": 1.5 } }, @@ -16161,6 +36056,41 @@ } }, "metadata": { + "description": "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "video", + "file", + "audio" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -16187,7 +36117,7 @@ "name": "Gemini 3.1 Pro Preview", "provider": "openrouter", "family": "gemini-pro", - "created_at": "2026-02-19 00:00:00 +0530", + "created_at": "2026-02-19 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -16207,7 +36137,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -16219,6 +36150,41 @@ } }, "metadata": { + "description": "Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "audio", + "file", + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -16250,7 +36216,7 @@ "name": "Gemini 3.1 Pro Preview Custom Tools", "provider": "openrouter", "family": "gemini-pro", - "created_at": "2026-02-19 00:00:00 +0530", + "created_at": "2026-02-19 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -16270,7 +36236,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -16282,6 +36249,41 @@ } }, "metadata": { + "description": "Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "audio", + "image", + "video", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -16308,12 +36310,74 @@ "knowledge": "2025-01" } }, + { + "id": "google/gemma-2-27b-it", + "name": "Google: Gemma 2 27B", + "provider": "openrouter", + "family": "google", + "created_at": "2024-07-13 00:00:00 UTC", + "context_window": 8192, + "max_output_tokens": 2048, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.65, + "output_per_million": 0.65 + } + } + }, + "metadata": { + "description": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 2048, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_p" + ] + } + }, { "id": "google/gemma-2-9b-it", "name": "Gemma 2 9B", "provider": "openrouter", "family": "gemma", - "created_at": "2024-06-28 00:00:00 +0530", + "created_at": "2024-06-28 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -16357,7 +36421,7 @@ "name": "Gemma 3 12B", "provider": "openrouter", "family": "gemma", - "created_at": "2025-03-13 00:00:00 +0530", + "created_at": "2025-03-13 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -16372,7 +36436,10 @@ }, "capabilities": [ "structured_output", - "vision" + "vision", + "streaming", + "function_calling", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -16383,6 +36450,42 @@ } }, "metadata": { + "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16405,7 +36508,7 @@ "name": "Gemma 3 12B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2025-03-13 00:00:00 +0530", + "created_at": "2025-03-13 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -16445,7 +36548,7 @@ "name": "Gemma 3 27B", "provider": "openrouter", "family": "gemma", - "created_at": "2025-03-12 00:00:00 +0530", + "created_at": "2025-03-12 00:00:00 UTC", "context_window": 96000, "max_output_tokens": 96000, "knowledge_cutoff": null, @@ -16461,7 +36564,9 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -16472,6 +36577,42 @@ } }, "metadata": { + "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16494,7 +36635,7 @@ "name": "Gemma 3 27B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2025-03-12 00:00:00 +0530", + "created_at": "2025-03-12 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -16535,7 +36676,7 @@ "name": "Gemma 3 4B", "provider": "openrouter", "family": "gemma", - "created_at": "2025-03-13 00:00:00 +0530", + "created_at": "2025-03-13 00:00:00 UTC", "context_window": 96000, "max_output_tokens": 96000, "knowledge_cutoff": null, @@ -16549,7 +36690,10 @@ ] }, "capabilities": [ - "vision" + "vision", + "streaming", + "structured_output", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -16560,6 +36704,40 @@ } }, "metadata": { + "description": "Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemini", + "instruct_type": "gemma" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16582,7 +36760,7 @@ "name": "Gemma 3 4B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2025-03-13 00:00:00 +0530", + "created_at": "2025-03-13 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -16622,7 +36800,7 @@ "name": "Gemma 3n 2B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2025-07-09 00:00:00 +0530", + "created_at": "2025-07-09 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 2000, "knowledge_cutoff": null, @@ -16659,7 +36837,7 @@ "name": "Gemma 3n 4B", "provider": "openrouter", "family": "gemma", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -16671,7 +36849,10 @@ "text" ] }, - "capabilities": [], + "capabilities": [ + "streaming", + "predicted_outputs" + ], "pricing": { "text_tokens": { "standard": { @@ -16681,6 +36862,36 @@ } }, "metadata": { + "description": "Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16703,7 +36914,7 @@ "name": "Gemma 3n 4B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 2000, "knowledge_cutoff": null, @@ -16740,7 +36951,7 @@ "name": "Gemma 4 26B A4B", "provider": "openrouter", "family": "gemma", - "created_at": "2026-04-03 00:00:00 +0530", + "created_at": "2026-04-03 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -16758,7 +36969,9 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -16769,6 +36982,47 @@ } }, "metadata": { + "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemma", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16791,7 +37045,7 @@ "name": "Gemma 4 26B A4B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2026-04-03 00:00:00 +0530", + "created_at": "2026-04-03 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -16809,10 +37063,42 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": {}, "metadata": { + "description": "Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemma", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16835,7 +37121,7 @@ "name": "Gemma 4 31B", "provider": "openrouter", "family": "gemma", - "created_at": "2026-04-02 00:00:00 +0530", + "created_at": "2026-04-02 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -16853,7 +37139,9 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -16864,6 +37152,47 @@ } }, "metadata": { + "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemma", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16886,7 +37215,7 @@ "name": "Gemma 4 31B (free)", "provider": "openrouter", "family": "gemma", - "created_at": "2026-04-02 00:00:00 +0530", + "created_at": "2026-04-02 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -16904,10 +37233,42 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": {}, "metadata": { + "description": "Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Gemma", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -16925,12 +37286,315 @@ "knowledge": "2025-01" } }, + { + "id": "google/lyria-3-clip-preview", + "name": "Google: Lyria 3 Clip Preview", + "provider": "openrouter", + "family": "google", + "created_at": "2026-03-30 21:47:35 UTC", + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "audio" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": {}, + "metadata": { + "description": "30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...", + "architecture": { + "modality": "text+image->text+audio", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text", + "audio" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "temperature", + "top_p" + ] + } + }, + { + "id": "google/lyria-3-pro-preview", + "name": "Google: Lyria 3 Pro Preview", + "provider": "openrouter", + "family": "google", + "created_at": "2026-03-30 21:48:06 UTC", + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text", + "audio" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": {}, + "metadata": { + "description": "Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...", + "architecture": { + "modality": "text+image->text+audio", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text", + "audio" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "temperature", + "top_p" + ] + } + }, + { + "id": "gryphe/mythomax-l2-13b", + "name": "MythoMax 13B", + "provider": "openrouter", + "family": "gryphe", + "created_at": "2023-07-02 00:00:00 UTC", + "context_window": 4096, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.06, + "output_per_million": 0.06 + } + } + }, + "metadata": { + "description": "One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama2", + "instruct_type": "alpaca" + }, + "top_provider": { + "context_length": 4096, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "ibm-granite/granite-4.0-h-micro", + "name": "IBM: Granite 4.0 Micro", + "provider": "openrouter", + "family": "ibm-granite", + "created_at": "2025-10-20 02:34:55 UTC", + "context_window": 131000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.017, + "output_per_million": 0.11 + } + } + }, + "metadata": { + "description": "Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "ibm-granite/granite-4.1-8b", + "name": "IBM: Granite 4.1 8B", + "provider": "openrouter", + "family": "ibm-granite", + "created_at": "2026-04-30 19:24:31 UTC", + "context_window": 131072, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.049999999999999996, + "output_per_million": 0.09999999999999999, + "cache_read_input_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "inception/mercury-2", "name": "Mercury 2", "provider": "openrouter", "family": "mercury", - "created_at": "2026-03-04 00:00:00 +0530", + "created_at": "2026-03-04 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 50000, "knowledge_cutoff": null, @@ -16945,18 +37609,48 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.25, "output_per_million": 0.75, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "description": "Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 50000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -16979,7 +37673,7 @@ "name": "Mercury Edit 2", "provider": "openrouter", "family": null, - "created_at": "2026-03-30 00:00:00 +0530", + "created_at": "2026-03-30 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -16999,7 +37693,7 @@ "standard": { "input_per_million": 0.25, "output_per_million": 0.75, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -17021,12 +37715,380 @@ } } }, + { + "id": "inclusionai/ling-2.6-1t:free", + "name": "inclusionAI: Ling-2.6-1T (free)", + "provider": "openrouter", + "family": "inclusionai", + "created_at": "2026-04-23 12:43:58 UTC", + "context_window": 262144, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "description": "Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "inclusionai/ling-2.6-flash", + "name": "inclusionAI: Ling-2.6-flash", + "provider": "openrouter", + "family": "inclusionai", + "created_at": "2026-04-21 18:24:46 UTC", + "context_window": 262144, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.08, + "output_per_million": 0.24, + "cache_read_input_per_million": 0.016 + } + } + }, + "metadata": { + "description": "Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "inflection/inflection-3-pi", + "name": "Inflection: Inflection 3 Pi", + "provider": "openrouter", + "family": "inflection", + "created_at": "2024-10-11 00:00:00 UTC", + "context_window": 8000, + "max_output_tokens": 1024, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay. Pi...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 8000, + "max_completion_tokens": 1024, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "top_p" + ] + } + }, + { + "id": "inflection/inflection-3-productivity", + "name": "Inflection: Inflection 3 Productivity", + "provider": "openrouter", + "family": "inflection", + "created_at": "2024-10-11 00:00:00 UTC", + "context_window": 8000, + "max_output_tokens": 1024, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 8000, + "max_completion_tokens": 1024, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "top_p" + ] + } + }, + { + "id": "kwaipilot/kat-coder-pro-v2", + "name": "Kwaipilot: KAT-Coder-Pro V2", + "provider": "openrouter", + "family": "kwaipilot", + "created_at": "2026-03-27 22:08:30 UTC", + "context_window": 256000, + "max_output_tokens": 80000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 1.2, + "cache_read_input_per_million": 0.06 + } + } + }, + "metadata": { + "description": "KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 80000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "liquid/lfm-2-24b-a2b", + "name": "LiquidAI: LFM2-24B-A2B", + "provider": "openrouter", + "family": "liquid", + "created_at": "2026-02-25 19:45:11 UTC", + "context_window": 32768, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.03, + "output_per_million": 0.12 + } + } + }, + "metadata": { + "description": "LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "liquid/lfm-2.5-1.2b-instruct:free", "name": "LFM2.5-1.2B-Instruct (free)", "provider": "openrouter", "family": "liquid", - "created_at": "2026-01-20 00:00:00 +0530", + "created_at": "2026-01-20 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -17038,9 +38100,41 @@ "text" ] }, - "capabilities": [], + "capabilities": [ + "streaming" + ], "pricing": {}, "metadata": { + "description": "LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17063,7 +38157,7 @@ "name": "LFM2.5-1.2B-Thinking (free)", "provider": "openrouter", "family": "liquid", - "created_at": "2026-01-20 00:00:00 +0530", + "created_at": "2026-01-20 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -17076,10 +38170,43 @@ ] }, "capabilities": [ - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17097,12 +38224,348 @@ "knowledge": "2025-06" } }, + { + "id": "mancer/weaver", + "name": "Mancer: Weaver (alpha)", + "provider": "openrouter", + "family": "mancer", + "created_at": "2023-08-02 00:00:00 UTC", + "context_window": 8000, + "max_output_tokens": 2000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.75, + "output_per_million": 1.0 + } + } + }, + "metadata": { + "description": "An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama2", + "instruct_type": "alpaca" + }, + "top_provider": { + "context_length": 8000, + "max_completion_tokens": 2000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-3-70b-instruct", + "name": "Meta: Llama 3 70B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-04-18 00:00:00 UTC", + "context_window": 8192, + "max_output_tokens": 8000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.51, + "output_per_million": 0.74 + } + } + }, + "metadata": { + "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-3-8b-instruct", + "name": "Meta: Llama 3 8B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-04-18 00:00:00 UTC", + "context_window": 8192, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.03, + "output_per_million": 0.04 + } + } + }, + "metadata": { + "description": "Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-3.1-70b-instruct", + "name": "Meta: Llama 3.1 70B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-07-23 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.39999999999999997, + "output_per_million": 0.39999999999999997 + } + } + }, + "metadata": { + "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-3.1-8b-instruct", + "name": "Meta: Llama 3.1 8B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-07-23 00:00:00 UTC", + "context_window": 16384, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.02, + "output_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 16384, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, { "id": "meta-llama/llama-3.2-11b-vision-instruct", "name": "Llama 3.2 11B Vision Instruct", "provider": "openrouter", "family": "llama", - "created_at": "2024-09-25 00:00:00 +0530", + "created_at": "2024-09-25 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -17116,10 +38579,53 @@ ] }, "capabilities": [ - "vision" + "vision", + "streaming", + "structured_output", + "predicted_outputs" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.245, + "output_per_million": 0.245 + } + } + }, "metadata": { + "description": "Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17137,12 +38643,130 @@ "knowledge": "2023-12" } }, + { + "id": "meta-llama/llama-3.2-1b-instruct", + "name": "Meta: Llama 3.2 1B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 60000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.027, + "output_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 60000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-3.2-3b-instruct", + "name": "Meta: Llama 3.2 3B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-09-25 00:00:00 UTC", + "context_window": 80000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.051, + "output_per_million": 0.33999999999999997 + } + } + }, + "metadata": { + "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 80000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "meta-llama/llama-3.2-3b-instruct:free", "name": "Llama 3.2 3B Instruct (free)", "provider": "openrouter", "family": "llama", - "created_at": "2024-09-25 00:00:00 +0530", + "created_at": "2024-09-25 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17156,10 +38780,38 @@ ] }, "capabilities": [ - "vision" + "vision", + "streaming" ], "pricing": {}, "metadata": { + "description": "Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17177,12 +38829,81 @@ "knowledge": "2023-12" } }, + { + "id": "meta-llama/llama-3.3-70b-instruct", + "name": "Meta: Llama 3.3 70B Instruct", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2024-12-06 17:28:57 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.32 + } + } + }, + "metadata": { + "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "meta-llama/llama-3.3-70b-instruct:free", "name": "Llama 3.3 70B Instruct (free)", "provider": "openrouter", "family": "llama", - "created_at": "2024-12-06 00:00:00 +0530", + "created_at": "2024-12-06 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17196,10 +38917,40 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": {}, "metadata": { + "description": "The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17217,12 +38968,469 @@ "knowledge": "2024-12" } }, + { + "id": "meta-llama/llama-4-maverick", + "name": "Meta: Llama 4 Maverick", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2025-04-05 19:37:02 UTC", + "context_window": 1048576, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "description": "Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama4", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-4-scout", + "name": "Meta: Llama 4 Scout", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2025-04-05 19:31:59 UTC", + "context_window": 327680, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.08, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "description": "Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama4", + "instruct_type": null + }, + "top_provider": { + "context_length": 327680, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-guard-3-8b", + "name": "Llama Guard 3 8B", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2025-02-12 23:01:58 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.48, + "output_per_million": 0.03 + } + } + }, + "metadata": { + "description": "Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification)...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "none" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "meta-llama/llama-guard-4-12b", + "name": "Meta: Llama Guard 4 12B", + "provider": "openrouter", + "family": "meta-llama", + "created_at": "2025-04-30 01:06:33 UTC", + "context_window": 163840, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.18, + "output_per_million": 0.18 + } + } + }, + "metadata": { + "description": "Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "microsoft/phi-4", + "name": "Microsoft: Phi 4", + "provider": "openrouter", + "family": "microsoft", + "created_at": "2025-01-10 06:17:52 UTC", + "context_window": 16384, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.065, + "output_per_million": 0.14 + } + } + }, + "metadata": { + "description": "[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 16384, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "microsoft/phi-4-mini-instruct", + "name": "Microsoft: Phi 4 Mini Instruct", + "provider": "openrouter", + "family": "microsoft", + "created_at": "2025-10-17 18:34:09 UTC", + "context_window": 128000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.08, + "output_per_million": 0.35, + "cache_read_input_per_million": 0.08 + } + } + }, + "metadata": { + "description": "Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "microsoft/wizardlm-2-8x22b", + "name": "WizardLM-2 8x22B", + "provider": "openrouter", + "family": "microsoft", + "created_at": "2024-04-16 00:00:00 UTC", + "context_window": 65535, + "max_output_tokens": 8000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.62, + "output_per_million": 0.62 + } + } + }, + "metadata": { + "description": "WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": "vicuna" + }, + "top_provider": { + "context_length": 65535, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "minimax/minimax-01", "name": "MiniMax-01", "provider": "openrouter", "family": "minimax", - "created_at": "2025-01-15 00:00:00 +0530", + "created_at": "2025-01-15 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 1000000, "knowledge_cutoff": null, @@ -17238,7 +39446,8 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -17249,6 +39458,30 @@ } }, "metadata": { + "description": "MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000192, + "max_completion_tokens": 1000192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "temperature", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17270,7 +39503,7 @@ "name": "MiniMax M1", "provider": "openrouter", "family": "minimax", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 40000, "knowledge_cutoff": null, @@ -17284,7 +39517,8 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -17295,6 +39529,39 @@ } }, "metadata": { + "description": "MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 40000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17316,7 +39583,7 @@ "name": "MiniMax M2", "provider": "openrouter", "family": "minimax", - "created_at": "2025-10-23 00:00:00 +0530", + "created_at": "2025-10-23 00:00:00 UTC", "context_window": 196600, "max_output_tokens": 118000, "knowledge_cutoff": null, @@ -17331,18 +39598,58 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.28, "output_per_million": 1.15, - "cached_input_per_million": 0.28 + "cache_read_input_per_million": 0.28, + "cache_write_input_per_million": 1.15 } } }, "metadata": { + "description": "MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 196608, + "max_completion_tokens": 196608, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17364,12 +39671,67 @@ } } }, + { + "id": "minimax/minimax-m2-her", + "name": "MiniMax: MiniMax M2-her", + "provider": "openrouter", + "family": "minimax", + "created_at": "2026-01-23 14:07:19 UTC", + "context_window": 65536, + "max_output_tokens": 2048, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 1.2, + "cache_read_input_per_million": 0.03 + } + } + }, + "metadata": { + "description": "MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 2048, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "temperature", + "top_p" + ] + } + }, { "id": "minimax/minimax-m2.1", "name": "MiniMax M2.1", "provider": "openrouter", "family": "minimax", - "created_at": "2025-12-23 00:00:00 +0530", + "created_at": "2025-12-23 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17384,7 +39746,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -17395,6 +39759,43 @@ } }, "metadata": { + "description": "MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 196608, + "max_completion_tokens": 196608, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17419,7 +39820,7 @@ "name": "MiniMax M2.5", "provider": "openrouter", "family": "minimax", - "created_at": "2026-02-12 00:00:00 +0530", + "created_at": "2026-02-12 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17434,18 +39835,61 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 1.2, - "cached_input_per_million": 0.03 + "cache_read_input_per_million": 0.03 } } }, "metadata": { + "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 196608, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17471,7 +39915,7 @@ "name": "MiniMax M2.5 (free)", "provider": "openrouter", "family": "minimax", - "created_at": "2026-02-12 00:00:00 +0530", + "created_at": "2026-02-12 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17486,10 +39930,39 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 196608, + "max_completion_tokens": 8192, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "temperature", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17514,7 +39987,7 @@ "name": "MiniMax M2.7", "provider": "openrouter", "family": "minimax", - "created_at": "2026-03-18 00:00:00 +0530", + "created_at": "2026-03-18 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17528,18 +40001,61 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 1.2, - "cached_input_per_million": 0.06 + "cache_read_input_per_million": 0.06, + "cache_write_input_per_million": 0.375 } } }, "metadata": { + "description": "MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 196608, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17563,7 +40079,7 @@ "name": "Codestral 2508", "provider": "openrouter", "family": "codestral", - "created_at": "2025-08-01 00:00:00 +0530", + "created_at": "2025-08-01 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -17577,7 +40093,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -17588,6 +40105,37 @@ } }, "metadata": { + "description": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17610,7 +40158,7 @@ "name": "Devstral 2 2512", "provider": "openrouter", "family": "devstral", - "created_at": "2025-09-12 00:00:00 +0530", + "created_at": "2025-09-12 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -17624,7 +40172,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -17635,6 +40184,37 @@ } }, "metadata": { + "description": "Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17652,12 +40232,77 @@ "knowledge": "2025-12" } }, + { + "id": "mistralai/devstral-medium", + "name": "Mistral: Devstral Medium", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-07-10 15:28:41 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.39999999999999997, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.04 + } + } + }, + "metadata": { + "description": "Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "mistralai/devstral-medium-2507", "name": "Devstral Medium", "provider": "openrouter", "family": "devstral", - "created_at": "2025-07-10 00:00:00 +0530", + "created_at": "2025-07-10 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17699,12 +40344,77 @@ "knowledge": "2025-05" } }, + { + "id": "mistralai/devstral-small", + "name": "Mistral: Devstral Small 1.1", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-07-10 15:19:11 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.3, + "cache_read_input_per_million": 0.01 + } + } + }, + "metadata": { + "description": "Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "mistralai/devstral-small-2505", "name": "Devstral Small", "provider": "openrouter", "family": "devstral", - "created_at": "2025-05-07 00:00:00 +0530", + "created_at": "2025-05-07 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -17750,7 +40460,7 @@ "name": "Devstral Small 1.1", "provider": "openrouter", "family": "devstral", - "created_at": "2025-07-10 00:00:00 +0530", + "created_at": "2025-07-10 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17792,12 +40502,543 @@ "knowledge": "2025-05" } }, + { + "id": "mistralai/ministral-14b-2512", + "name": "Mistral: Ministral 3 14B 2512", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-12-02 13:22:15 UTC", + "context_window": 262144, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.19999999999999998, + "output_per_million": 0.19999999999999998, + "cache_read_input_per_million": 0.02 + } + } + }, + "metadata": { + "description": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "mistralai/ministral-3b-2512", + "name": "Mistral: Ministral 3 3B 2512", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-12-02 13:19:20 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.09999999999999999, + "cache_read_input_per_million": 0.01 + } + } + }, + "metadata": { + "description": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "mistralai/ministral-8b-2512", + "name": "Mistral: Ministral 3 8B 2512", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-12-02 13:20:54 UTC", + "context_window": 262144, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.15, + "cache_read_input_per_million": 0.015 + } + } + }, + "metadata": { + "description": "A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-7b-instruct-v0.1", + "name": "Mistral: Mistral 7B Instruct v0.1", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2023-09-28 00:00:00 UTC", + "context_window": 2824, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.11, + "output_per_million": 0.19 + } + } + }, + "metadata": { + "description": "A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "top_provider": { + "context_length": 2824, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-large", + "name": "Mistral Large", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2024-02-26 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 6.0, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-large-2407", + "name": "Mistral Large 2407", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2024-11-19 01:06:55 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 6.0, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-large-2411", + "name": "Mistral Large 2411", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2024-11-19 01:11:25 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 6.0, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the previous [Mistral Large 24.07](/mistralai/mistral-large-2407), with notable...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-large-2512", + "name": "Mistral: Mistral Large 3 2512", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-12-01 21:27:52 UTC", + "context_window": 262144, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5, + "cache_read_input_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "mistralai/mistral-medium-3", "name": "Mistral Medium 3", "provider": "openrouter", "family": "mistral-medium", - "created_at": "2025-05-07 00:00:00 +0530", + "created_at": "2025-05-07 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -17813,7 +41054,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -17824,6 +41066,38 @@ } }, "metadata": { + "description": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -17841,12 +41115,80 @@ "knowledge": "2025-05" } }, + { + "id": "mistralai/mistral-medium-3-5", + "name": "Mistral: Mistral Medium 3.5", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2026-04-30 17:33:59 UTC", + "context_window": 262144, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.5, + "output_per_million": 7.5 + } + } + }, + "metadata": { + "description": "Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "mistralai/mistral-medium-3.1", "name": "Mistral Medium 3.1", "provider": "openrouter", "family": "mistral-medium", - "created_at": "2025-08-12 00:00:00 +0530", + "created_at": "2025-08-12 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -17862,7 +41204,8 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -17873,6 +41216,38 @@ } }, "metadata": { + "description": "Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -17890,12 +41265,214 @@ "knowledge": "2025-05" } }, + { + "id": "mistralai/mistral-nemo", + "name": "Mistral: Mistral Nemo", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2024-07-19 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.02, + "output_per_million": 0.03 + } + } + }, + "metadata": { + "description": "A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-saba", + "name": "Mistral: Saba", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-02-17 14:40:39 UTC", + "context_window": 32768, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.19999999999999998, + "output_per_million": 0.6, + "cache_read_input_per_million": 0.02 + } + } + }, + "metadata": { + "description": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "mistralai/mistral-small-24b-instruct-2501", + "name": "Mistral: Mistral Small 3", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-01-30 16:43:29 UTC", + "context_window": 32768, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.049999999999999996, + "output_per_million": 0.08 + } + } + }, + "metadata": { + "description": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "mistralai/mistral-small-2603", "name": "Mistral Small 4", "provider": "openrouter", "family": "mistral-small", - "created_at": "2026-03-16 00:00:00 +0530", + "created_at": "2026-03-16 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -17911,7 +41488,9 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { @@ -17922,6 +41501,41 @@ } }, "metadata": { + "description": "Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17944,7 +41558,7 @@ "name": "Mistral Small 3.1 24B Instruct", "provider": "openrouter", "family": "mistral-small", - "created_at": "2025-03-17 00:00:00 +0530", + "created_at": "2025-03-17 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -17960,10 +41574,47 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.35, + "output_per_million": 0.56 + } + } + }, "metadata": { + "description": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -17986,7 +41637,7 @@ "name": "Mistral Small 3.2 24B Instruct", "provider": "openrouter", "family": "mistral-small", - "created_at": "2025-06-20 00:00:00 +0530", + "created_at": "2025-06-20 00:00:00 UTC", "context_window": 96000, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -18002,10 +41653,55 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming", + "predicted_outputs" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.19999999999999998 + } + } + }, "metadata": { + "description": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18023,12 +41719,280 @@ "knowledge": "2024-10" } }, + { + "id": "mistralai/mixtral-8x22b-instruct", + "name": "Mistral: Mixtral 8x22B Instruct", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2024-04-17 00:00:00 UTC", + "context_window": 65536, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 6.0, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "mistralai/mixtral-8x7b-instruct", + "name": "Mistral: Mixtral 8x7B Instruct", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2023-12-10 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.54, + "output_per_million": 0.54 + } + } + }, + "metadata": { + "description": "Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "mistralai/pixtral-large-2411", + "name": "Mistral: Pixtral Large 2411", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2024-11-19 00:49:48 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 6.0, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "mistralai/voxtral-small-24b-2507", + "name": "Mistral: Voxtral Small 24B 2507", + "provider": "openrouter", + "family": "mistralai", + "created_at": "2025-10-30 14:39:04 UTC", + "context_window": 32000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.3, + "cache_read_input_per_million": 0.01 + } + } + }, + "metadata": { + "description": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...", + "architecture": { + "modality": "text+audio->text", + "input_modalities": [ + "text", + "audio" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": null + }, + "top_provider": { + "context_length": 32000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "moonshotai/kimi-k2", "name": "Kimi K2", "provider": "openrouter", "family": "kimi", - "created_at": "2025-07-11 00:00:00 +0530", + "created_at": "2025-07-11 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -18041,7 +42005,8 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming" ], "pricing": { "text_tokens": { @@ -18052,6 +42017,37 @@ } }, "metadata": { + "description": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18074,7 +42070,7 @@ "name": "Kimi K2 Instruct 0905", "provider": "openrouter", "family": "kimi", - "created_at": "2025-09-05 00:00:00 +0530", + "created_at": "2025-09-05 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -18088,7 +42084,9 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -18099,6 +42097,41 @@ } }, "metadata": { + "description": "Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18121,7 +42154,7 @@ "name": "Kimi K2 Instruct 0905 (exacto)", "provider": "openrouter", "family": "kimi", - "created_at": "2025-09-05 00:00:00 +0530", + "created_at": "2025-09-05 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -18168,7 +42201,7 @@ "name": "Kimi K2 Thinking", "provider": "openrouter", "family": "kimi-thinking", - "created_at": "2025-11-06 00:00:00 +0530", + "created_at": "2025-11-06 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -18183,18 +42216,57 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.6, "output_per_million": 2.5, - "cached_input_per_million": 0.15 + "cache_read_input_per_million": 0.15 } } }, "metadata": { + "description": "Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18221,7 +42293,7 @@ "name": "Kimi K2.5", "provider": "openrouter", "family": "kimi", - "created_at": "2026-01-27 00:00:00 +0530", + "created_at": "2026-01-27 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -18239,18 +42311,61 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.6, "output_per_million": 3, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1 } } }, "metadata": { + "description": "Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65535, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18272,12 +42387,409 @@ "knowledge": "2025-01" } }, + { + "id": "moonshotai/kimi-k2.6", + "name": "Kimi K2.6", + "provider": "openrouter", + "family": "kimi", + "created_at": "2026-04-20 00:00:00 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.95, + "output_per_million": 4, + "cache_read_input_per_million": 0.16 + } + } + }, + "metadata": { + "description": "Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-20", + "interleaved": { + "field": "reasoning_details" + }, + "cost": { + "input": 0.95, + "output": 4, + "cache_read": 0.16 + }, + "limit": { + "context": 262144, + "output": 262144 + } + } + }, + { + "id": "morph/morph-v3-fast", + "name": "Morph: Morph V3 Fast", + "provider": "openrouter", + "family": "morph", + "created_at": "2025-07-07 17:40:02 UTC", + "context_window": 81920, + "max_output_tokens": 38000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.7999999999999999, + "output_per_million": 1.2 + } + } + }, + "metadata": { + "description": "Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet}...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 81920, + "max_completion_tokens": 38000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature" + ] + } + }, + { + "id": "morph/morph-v3-large", + "name": "Morph: Morph V3 Large", + "provider": "openrouter", + "family": "morph", + "created_at": "2025-07-07 17:54:18 UTC", + "context_window": 262144, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.8999999999999999, + "output_per_million": 1.9 + } + } + }, + "metadata": { + "description": "Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code}...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature" + ] + } + }, + { + "id": "nex-agi/deepseek-v3.1-nex-n1", + "name": "Nex AGI: DeepSeek V3.1 Nex N1", + "provider": "openrouter", + "family": "nex-agi", + "created_at": "2025-12-08 14:33:13 UTC", + "context_window": 131072, + "max_output_tokens": 163840, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.135, + "output_per_million": 0.5 + } + } + }, + "metadata": { + "description": "DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonstrates competitive performance across...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 163840, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "nousresearch/hermes-2-pro-llama-3-8b", + "name": "NousResearch: Hermes 2 Pro - Llama-3 8B", + "provider": "openrouter", + "family": "nousresearch", + "created_at": "2024-05-27 00:00:00 UTC", + "context_window": 8192, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.14, + "output_per_million": 0.14 + } + } + }, + "metadata": { + "description": "Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "nousresearch/hermes-3-llama-3.1-405b", + "name": "Nous: Hermes 3 405B Instruct", + "provider": "openrouter", + "family": "nousresearch", + "created_at": "2024-08-16 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.0, + "output_per_million": 1.0 + } + } + }, + "metadata": { + "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "nousresearch/hermes-3-llama-3.1-405b:free", "name": "Hermes 3 405B Instruct (free)", "provider": "openrouter", "family": "hermes", - "created_at": "2024-08-16 00:00:00 +0530", + "created_at": "2024-08-16 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -18290,10 +42802,38 @@ ] }, "capabilities": [ - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "stop", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18311,12 +42851,78 @@ "knowledge": "2023-12" } }, + { + "id": "nousresearch/hermes-3-llama-3.1-70b", + "name": "Nous: Hermes 3 70B Instruct", + "provider": "openrouter", + "family": "nousresearch", + "created_at": "2024-08-18 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 0.3 + } + } + }, + "metadata": { + "description": "Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "nousresearch/hermes-4-405b", "name": "Hermes 4 405B", "provider": "openrouter", "family": "hermes", - "created_at": "2025-08-25 00:00:00 +0530", + "created_at": "2025-08-25 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -18330,7 +42936,9 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { @@ -18341,6 +42949,36 @@ } }, "metadata": { + "description": "Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18363,7 +43001,7 @@ "name": "Hermes 4 70B", "provider": "openrouter", "family": "hermes", - "created_at": "2025-08-25 00:00:00 +0530", + "created_at": "2025-08-25 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -18378,7 +43016,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -18389,6 +43028,36 @@ } }, "metadata": { + "description": "Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18406,12 +43075,220 @@ "knowledge": "2023-12" } }, + { + "id": "nvidia/llama-3.1-nemotron-70b-instruct", + "name": "NVIDIA: Llama 3.1 Nemotron 70B Instruct", + "provider": "openrouter", + "family": "nvidia", + "created_at": "2024-10-15 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.2, + "output_per_million": 1.2 + } + } + }, + "metadata": { + "description": "NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging [Llama 3.1 70B](/models/meta-llama/llama-3.1-70b-instruct) architecture and Reinforcement Learning from Human Feedback (RLHF), it excels...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "nvidia/llama-3.3-nemotron-super-49b-v1.5", + "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", + "provider": "openrouter", + "family": "nvidia", + "created_at": "2025-10-10 13:03:15 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.39999999999999997 + } + } + }, + "metadata": { + "description": "Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "nvidia/nemotron-3-nano-30b-a3b", + "name": "NVIDIA: Nemotron 3 Nano 30B A3B", + "provider": "openrouter", + "family": "nvidia", + "created_at": "2025-12-14 16:54:35 UTC", + "context_window": 262144, + "max_output_tokens": 228000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.049999999999999996, + "output_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 228000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "nvidia/nemotron-3-nano-30b-a3b:free", "name": "Nemotron 3 Nano 30B A3B (free)", "provider": "openrouter", "family": "nemotron", - "created_at": "2025-12-14 00:00:00 +0530", + "created_at": "2025-12-14 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -18426,10 +43303,39 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18447,12 +43353,88 @@ "knowledge": "2025-11" } }, + { + "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", + "name": "Nemotron 3 Nano Omni (free)", + "provider": "openrouter", + "family": "nemotron", + "created_at": "2026-04-28 00:00:00 UTC", + "context_window": 256000, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": {}, + "metadata": { + "description": "NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...", + "architecture": { + "modality": "text+image+audio+video->text", + "input_modalities": [ + "text", + "audio", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-28", + "cost": { + "input": 0, + "output": 0 + }, + "limit": { + "context": 256000, + "output": 65536 + } + } + }, { "id": "nvidia/nemotron-3-super-120b-a12b", "name": "Nemotron 3 Super", "provider": "openrouter", "family": "nemotron", - "created_at": "2026-03-11 00:00:00 +0530", + "created_at": "2026-03-11 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -18466,7 +43448,10 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -18477,6 +43462,44 @@ } }, "metadata": { + "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18499,7 +43522,7 @@ "name": "Nemotron 3 Super (free)", "provider": "openrouter", "family": "nemotron", - "created_at": "2026-03-11 00:00:00 +0530", + "created_at": "2026-03-11 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -18513,10 +43536,42 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": {}, "metadata": { + "description": "NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18534,12 +43589,83 @@ "knowledge": "2024-04" } }, + { + "id": "nvidia/nemotron-nano-12b-v2-vl", + "name": "NVIDIA: Nemotron Nano 12B 2 VL", + "provider": "openrouter", + "family": "nvidia", + "created_at": "2025-10-28 18:19:25 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.19999999999999998, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "nvidia/nemotron-nano-12b-v2-vl:free", "name": "Nemotron Nano 12B 2 VL (free)", "provider": "openrouter", "family": "nemotron", - "created_at": "2025-10-28 00:00:00 +0530", + "created_at": "2025-10-28 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -18555,10 +43681,41 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": {}, "metadata": { + "description": "NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18581,7 +43738,7 @@ "name": "nvidia-nemotron-nano-9b-v2", "provider": "openrouter", "family": "nemotron", - "created_at": "2025-08-18 00:00:00 +0530", + "created_at": "2025-08-18 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -18595,7 +43752,10 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -18606,6 +43766,42 @@ } }, "metadata": { + "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18628,7 +43824,7 @@ "name": "Nemotron Nano 9B V2 (free)", "provider": "openrouter", "family": "nemotron", - "created_at": "2025-09-05 00:00:00 +0530", + "created_at": "2025-09-05 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -18643,10 +43839,41 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -18664,12 +43891,616 @@ "knowledge": "2024-09" } }, + { + "id": "openai/gpt-3.5-turbo", + "name": "OpenAI: GPT-3.5 Turbo", + "provider": "openrouter", + "family": "openai", + "created_at": "2023-05-28 00:00:00 UTC", + "context_window": 16385, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 16385, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-3.5-turbo-0613", + "name": "OpenAI: GPT-3.5 Turbo (older v0613)", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-01-25 00:00:00 UTC", + "context_window": 4095, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.0, + "output_per_million": 2.0 + } + } + }, + "metadata": { + "description": "GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 4095, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-3.5-turbo-16k", + "name": "OpenAI: GPT-3.5 Turbo 16k", + "provider": "openrouter", + "family": "openai", + "created_at": "2023-08-28 00:00:00 UTC", + "context_window": 16385, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 4.0 + } + } + }, + "metadata": { + "description": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 16385, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-3.5-turbo-instruct", + "name": "OpenAI: GPT-3.5 Turbo Instruct", + "provider": "openrouter", + "family": "openai", + "created_at": "2023-09-28 00:00:00 UTC", + "context_window": 4095, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.5, + "output_per_million": 2.0 + } + } + }, + "metadata": { + "description": "This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 4095, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-4", + "name": "OpenAI: GPT-4", + "provider": "openrouter", + "family": "openai", + "created_at": "2023-05-28 00:00:00 UTC", + "context_window": 8191, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 30.0, + "output_per_million": 60.0 + } + } + }, + "metadata": { + "description": "OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 8191, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-4-0314", + "name": "OpenAI: GPT-4 (older v0314)", + "provider": "openrouter", + "family": "openai", + "created_at": "2023-05-28 00:00:00 UTC", + "context_window": 8191, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 30.0, + "output_per_million": 60.0 + } + } + }, + "metadata": { + "description": "GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 8191, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-4-1106-preview", + "name": "OpenAI: GPT-4 Turbo (older v1106)", + "provider": "openrouter", + "family": "openai", + "created_at": "2023-11-06 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 30.0 + } + } + }, + "metadata": { + "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to April 2023.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-4-turbo", + "name": "OpenAI: GPT-4 Turbo", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-04-09 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 30.0 + } + } + }, + "metadata": { + "description": "The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-4-turbo-preview", + "name": "OpenAI: GPT-4 Turbo Preview", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-01-25 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 30.0 + } + } + }, + "metadata": { + "description": "The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, { "id": "openai/gpt-4.1", "name": "GPT-4.1", "provider": "openrouter", "family": "gpt", - "created_at": "2025-04-14 00:00:00 +0530", + "created_at": "2025-04-14 00:00:00 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -18685,18 +44516,50 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2, "output_per_million": 8, - "cached_input_per_million": 0.5 + "cache_read_input_per_million": 0.5 } } }, "metadata": { + "description": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1047576, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -18720,7 +44583,7 @@ "name": "GPT-4.1 Mini", "provider": "openrouter", "family": "gpt-mini", - "created_at": "2025-04-14 00:00:00 +0530", + "created_at": "2025-04-14 00:00:00 UTC", "context_window": 1047576, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -18736,18 +44599,50 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.4, "output_per_million": 1.6, - "cached_input_per_million": 0.1 + "cache_read_input_per_million": 0.1 } } }, "metadata": { + "description": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -18766,12 +44661,443 @@ "knowledge": "2024-04" } }, + { + "id": "openai/gpt-4.1-nano", + "name": "OpenAI: GPT-4.1 Nano", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-04-14 17:22:49 UTC", + "context_window": 1047576, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.39999999999999997, + "cache_read_input_per_million": 0.024999999999999998 + } + } + }, + "metadata": { + "description": "For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1047576, + "max_completion_tokens": 32768, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "openai/gpt-4o", + "name": "OpenAI: GPT-4o", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-05-13 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "openai/gpt-4o-2024-05-13", + "name": "OpenAI: GPT-4o (2024-05-13)", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-05-13 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 15.0 + } + } + }, + "metadata": { + "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "openai/gpt-4o-2024-08-06", + "name": "OpenAI: GPT-4o (2024-08-06)", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-08-06 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0, + "cache_read_input_per_million": 1.25 + } + } + }, + "metadata": { + "description": "The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "openai/gpt-4o-2024-11-20", + "name": "OpenAI: GPT-4o (2024-11-20)", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-11-20 18:33:14 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0, + "cache_read_input_per_million": 1.25 + } + } + }, + "metadata": { + "description": "The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "openai/gpt-4o-audio-preview", + "name": "OpenAI: GPT-4o Audio", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-08-15 04:44:21 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "audio", + "text" + ], + "output": [ + "text", + "audio" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs...", + "architecture": { + "modality": "text+audio->text+audio", + "input_modalities": [ + "audio", + "text" + ], + "output_modalities": [ + "text", + "audio" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, { "id": "openai/gpt-4o-mini", "name": "GPT-4o-mini", "provider": "openrouter", "family": "gpt-mini", - "created_at": "2024-07-18 00:00:00 +0530", + "created_at": "2024-07-18 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -18787,18 +45113,57 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08 } } }, "metadata": { + "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -18817,12 +45182,197 @@ "knowledge": "2024-10" } }, + { + "id": "openai/gpt-4o-mini-2024-07-18", + "name": "OpenAI: GPT-4o-mini (2024-07-18)", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-07-18 00:00:00 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6, + "cache_read_input_per_million": 0.075 + } + } + }, + "metadata": { + "description": "GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "openai/gpt-4o-mini-search-preview", + "name": "OpenAI: GPT-4o-mini Search Preview", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-03-12 22:22:02 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6 + } + } + }, + "metadata": { + "description": "GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "structured_outputs", + "web_search_options" + ] + } + }, + { + "id": "openai/gpt-4o-search-preview", + "name": "OpenAI: GPT-4o Search Preview", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-03-12 22:19:09 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "structured_outputs", + "web_search_options" + ] + } + }, { "id": "openai/gpt-5", "name": "GPT-5", "provider": "openrouter", "family": "gpt", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-10-01", @@ -18839,7 +45389,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -18850,6 +45401,37 @@ } }, "metadata": { + "description": "GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -18872,7 +45454,7 @@ "name": "GPT-5 Chat (latest)", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -18888,7 +45470,8 @@ "capabilities": [ "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -18899,6 +45482,32 @@ } }, "metadata": { + "description": "GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "response_format", + "seed", + "structured_outputs" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -18921,7 +45530,7 @@ "name": "GPT-5 Codex", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-09-15 00:00:00 +0530", + "created_at": "2025-09-15 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-10-01", @@ -18938,18 +45547,48 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "description": "GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -18973,7 +45612,7 @@ "name": "GPT-5 Image", "provider": "openrouter", "family": "gpt", - "created_at": "2025-10-14 00:00:00 +0530", + "created_at": "2025-10-14 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-10-01", @@ -18992,18 +45631,56 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 5, "output_per_million": 10, - "cached_input_per_million": 1.25 + "cache_read_input_per_million": 1.25 } } }, "metadata": { + "description": "[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...", + "architecture": { + "modality": "text+image+file->text+image", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "image", + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19022,12 +45699,85 @@ "knowledge": "2024-10-01" } }, + { + "id": "openai/gpt-5-image-mini", + "name": "OpenAI: GPT-5 Image Mini", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-10-16 14:23:03 UTC", + "context_window": 400000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "file", + "image", + "text" + ], + "output": [ + "image", + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 2.0, + "cache_read_input_per_million": 0.25 + } + } + }, + "metadata": { + "description": "GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...", + "architecture": { + "modality": "text+image+file->text+image", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "image", + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_logprobs", + "top_p" + ] + } + }, { "id": "openai/gpt-5-mini", "name": "GPT-5 Mini", "provider": "openrouter", "family": "gpt-mini", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-10-01", @@ -19044,7 +45794,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -19055,6 +45806,37 @@ } }, "metadata": { + "description": "GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19077,7 +45859,7 @@ "name": "GPT-5 Nano", "provider": "openrouter", "family": "gpt-nano", - "created_at": "2025-08-07 00:00:00 +0530", + "created_at": "2025-08-07 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-10-01", @@ -19094,7 +45876,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -19105,6 +45888,37 @@ } }, "metadata": { + "description": "GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19127,7 +45941,7 @@ "name": "GPT-5 Pro", "provider": "openrouter", "family": "gpt-pro", - "created_at": "2025-10-06 00:00:00 +0530", + "created_at": "2025-10-06 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 272000, "knowledge_cutoff": "2024-09-30", @@ -19144,7 +45958,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -19155,6 +45970,36 @@ } }, "metadata": { + "description": "GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19177,7 +46022,7 @@ "name": "GPT-5.1", "provider": "openrouter", "family": "gpt", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -19194,18 +46039,50 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "description": "GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19229,7 +46106,7 @@ "name": "GPT-5.1 Chat", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": "2024-09-30", @@ -19246,18 +46123,48 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "description": "GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19281,7 +46188,7 @@ "name": "GPT-5.1-Codex", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -19298,18 +46205,49 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.125 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "description": "GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19333,7 +46271,7 @@ "name": "GPT-5.1-Codex-Max", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2024-09-30", @@ -19350,18 +46288,49 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.1, "output_per_million": 9, - "cached_input_per_million": 0.11 + "cache_read_input_per_million": 0.11 } } }, "metadata": { + "description": "GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19385,7 +46354,7 @@ "name": "GPT-5.1-Codex-Mini", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-11-13 00:00:00 +0530", + "created_at": "2025-11-13 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 100000, "knowledge_cutoff": "2024-09-30", @@ -19402,18 +46371,49 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.25, "output_per_million": 2, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "description": "GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19437,7 +46437,7 @@ "name": "GPT-5.2", "provider": "openrouter", "family": "gpt", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19454,18 +46454,50 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, "metadata": { + "description": "GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19489,7 +46521,7 @@ "name": "GPT-5.2 Chat", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 16384, "knowledge_cutoff": "2025-08-31", @@ -19506,18 +46538,48 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, "metadata": { + "description": "GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 32000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19541,7 +46603,7 @@ "name": "GPT-5.2-Codex", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2026-01-14 00:00:00 +0530", + "created_at": "2026-01-14 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19558,18 +46620,49 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, "metadata": { + "description": "GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19593,7 +46686,7 @@ "name": "GPT-5.2 Pro", "provider": "openrouter", "family": "gpt-pro", - "created_at": "2025-12-11 00:00:00 +0530", + "created_at": "2025-12-11 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19610,7 +46703,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -19621,6 +46715,36 @@ } }, "metadata": { + "description": "GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19638,12 +46762,77 @@ "knowledge": "2025-08-31" } }, + { + "id": "openai/gpt-5.3-chat", + "name": "OpenAI: GPT-5.3 Chat", + "provider": "openrouter", + "family": "openai", + "created_at": "2026-03-03 18:54:21 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.75, + "output_per_million": 14.0, + "cache_read_input_per_million": 0.175 + } + } + }, + "metadata": { + "description": "GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_completion_tokens", + "max_tokens", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, { "id": "openai/gpt-5.3-codex", "name": "GPT-5.3-Codex", "provider": "openrouter", "family": "gpt-codex", - "created_at": "2026-02-24 00:00:00 +0530", + "created_at": "2026-02-24 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19661,18 +46850,50 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.75, "output_per_million": 14, - "cached_input_per_million": 0.175 + "cache_read_input_per_million": 0.175 } } }, "metadata": { + "description": "GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19696,7 +46917,7 @@ "name": "GPT-5.4", "provider": "openrouter", "family": "gpt", - "created_at": "2026-03-05 00:00:00 +0530", + "created_at": "2026-03-05 00:00:00 UTC", "context_window": 1050000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19714,18 +46935,50 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2.5, "output_per_million": 15, - "cached_input_per_million": 0.25 + "cache_read_input_per_million": 0.25 } } }, "metadata": { + "description": "GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19750,12 +47003,83 @@ "knowledge": "2025-08-31" } }, + { + "id": "openai/gpt-5.4-image-2", + "name": "OpenAI: GPT-5.4 Image 2", + "provider": "openrouter", + "family": "openai", + "created_at": "2026-04-21 18:52:08 UTC", + "context_window": 272000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "file" + ], + "output": [ + "image", + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 8.0, + "output_per_million": 15.0, + "cache_read_input_per_million": 2.0 + } + } + }, + "metadata": { + "description": "[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...", + "architecture": { + "modality": "text+image+file->text+image", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "image", + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 272000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "top_logprobs" + ] + } + }, { "id": "openai/gpt-5.4-mini", "name": "GPT-5.4 Mini", "provider": "openrouter", "family": "gpt-mini", - "created_at": "2026-03-17 00:00:00 +0530", + "created_at": "2026-03-17 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19773,18 +47097,50 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.00000075, - "output_per_million": 0.0000045, - "cached_input_per_million": 0.000000075 + "input_per_million": 0.75, + "output_per_million": 4.5, + "cache_read_input_per_million": 0.075 } } }, "metadata": { + "description": "GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19792,9 +47148,9 @@ "temperature": true, "last_updated": "2026-03-17", "cost": { - "input": 0.00000075, - "output": 0.0000045, - "cache_read": 0.000000075 + "input": 0.75, + "output": 4.5, + "cache_read": 0.075 }, "limit": { "context": 400000, @@ -19808,7 +47164,7 @@ "name": "GPT-5.4 Nano", "provider": "openrouter", "family": "gpt-nano", - "created_at": "2026-03-17 00:00:00 +0530", + "created_at": "2026-03-17 00:00:00 UTC", "context_window": 400000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19825,18 +47181,50 @@ "capabilities": [ "function_calling", "structured_output", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.0000002, - "output_per_million": 0.00000125, - "cached_input_per_million": 0.00000002 + "input_per_million": 0.2, + "output_per_million": 1.25, + "cache_read_input_per_million": 0.02 } } }, "metadata": { + "description": "GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19844,9 +47232,9 @@ "temperature": true, "last_updated": "2026-03-17", "cost": { - "input": 0.0000002, - "output": 0.00000125, - "cache_read": 0.00000002 + "input": 0.2, + "output": 1.25, + "cache_read": 0.02 }, "limit": { "context": 400000, @@ -19860,7 +47248,7 @@ "name": "GPT-5.4 Pro", "provider": "openrouter", "family": "gpt-pro", - "created_at": "2026-03-05 00:00:00 +0530", + "created_at": "2026-03-05 00:00:00 UTC", "context_window": 1050000, "max_output_tokens": 128000, "knowledge_cutoff": "2025-08-31", @@ -19877,18 +47265,51 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 30, "output_per_million": 180, - "cached_input_per_million": 30 + "cache_read_input_per_million": 30 } } }, "metadata": { + "description": "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -19908,12 +47329,402 @@ "knowledge": "2025-08-31" } }, + { + "id": "openai/gpt-5.5", + "name": "GPT-5.5", + "provider": "openrouter", + "family": "gpt", + "created_at": "2026-04-23 00:00:00 UTC", + "context_window": 1050000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2025-12-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 30, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "description": "GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-23", + "cost": { + "input": 5, + "output": 30, + "cache_read": 0.5, + "context_over_200k": { + "input": 10, + "output": 45, + "cache_read": 1 + } + }, + "limit": { + "context": 1050000, + "input": 922000, + "output": 128000 + }, + "knowledge": "2025-12-01" + } + }, + { + "id": "openai/gpt-5.5-pro", + "name": "GPT-5.5 Pro", + "provider": "openrouter", + "family": "gpt-pro", + "created_at": "2026-04-23 00:00:00 UTC", + "context_window": 1050000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2025-12-01", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 30, + "output_per_million": 180 + } + } + }, + "metadata": { + "description": "GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-23", + "cost": { + "input": 30, + "output": 180, + "context_over_200k": { + "input": 60, + "output": 270 + } + }, + "limit": { + "context": 1050000, + "input": 922000, + "output": 128000 + }, + "knowledge": "2025-12-01" + } + }, + { + "id": "openai/gpt-audio", + "name": "OpenAI: GPT Audio", + "provider": "openrouter", + "family": "openai", + "created_at": "2026-01-19 22:42:49 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.5, + "output_per_million": 10.0 + } + } + }, + "metadata": { + "description": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...", + "architecture": { + "modality": "text+audio->text+audio", + "input_modalities": [ + "text", + "audio" + ], + "output_modalities": [ + "text", + "audio" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-audio-mini", + "name": "OpenAI: GPT Audio Mini", + "provider": "openrouter", + "family": "openai", + "created_at": "2026-01-19 21:50:19 UTC", + "context_window": 128000, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "audio" + ], + "output": [ + "text", + "audio" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 2.4 + } + } + }, + "metadata": { + "description": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...", + "architecture": { + "modality": "text+audio->text+audio", + "input_modalities": [ + "text", + "audio" + ], + "output_modalities": [ + "text", + "audio" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": 16384, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/gpt-chat-latest", + "name": "OpenAI: GPT Chat Latest", + "provider": "openrouter", + "family": "openai", + "created_at": "2026-05-05 16:56:52 UTC", + "context_window": 400000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 30.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "description": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "tool_choice", + "tools", + "top_logprobs" + ] + } + }, { "id": "openai/gpt-oss-120b", "name": "GPT OSS 120B", "provider": "openrouter", "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -19928,7 +47739,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -19939,6 +47752,45 @@ } }, "metadata": { + "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -19960,7 +47812,7 @@ "name": "GPT OSS 120B (exacto)", "provider": "openrouter", "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20007,7 +47859,7 @@ "name": "gpt-oss-120b (free)", "provider": "openrouter", "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20021,10 +47873,39 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "stop", + "temperature", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20046,7 +47927,7 @@ "name": "GPT OSS 20B", "provider": "openrouter", "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20061,7 +47942,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20072,6 +47955,45 @@ } }, "metadata": { + "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20093,7 +48015,7 @@ "name": "gpt-oss-20b (free)", "provider": "openrouter", "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", + "created_at": "2025-08-05 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20107,10 +48029,39 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming" ], "pricing": {}, "metadata": { + "description": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 8192, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "stop", + "temperature", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20132,7 +48083,7 @@ "name": "GPT OSS Safeguard 20B", "provider": "openrouter", "family": "gpt-oss", - "created_at": "2025-10-29 00:00:00 +0530", + "created_at": "2025-10-29 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -20146,7 +48097,9 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { @@ -20157,6 +48110,36 @@ } }, "metadata": { + "description": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -20173,12 +48156,473 @@ } } }, + { + "id": "openai/o1", + "name": "OpenAI: o1", + "provider": "openrouter", + "family": "openai", + "created_at": "2024-12-17 18:26:39 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 15.0, + "output_per_million": 60.0, + "cache_read_input_per_million": 7.5 + } + } + }, + "metadata": { + "description": "The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, + { + "id": "openai/o1-pro", + "name": "OpenAI: o1-pro", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-03-19 22:26:51 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 150.0, + "output_per_million": 600.0 + } + } + }, + "metadata": { + "description": "The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs" + ] + } + }, + { + "id": "openai/o3", + "name": "OpenAI: o3", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-04-16 17:10:57 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "description": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, + { + "id": "openai/o3-deep-research", + "name": "OpenAI: o3 Deep Research", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-10-10 20:54:21 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 10.0, + "output_per_million": 40.0, + "cache_read_input_per_million": 2.5 + } + } + }, + "metadata": { + "description": "o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/o3-mini", + "name": "OpenAI: o3 Mini", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-01-31 19:28:41 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4, + "cache_read_input_per_million": 0.55 + } + } + }, + "metadata": { + "description": "OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...", + "architecture": { + "modality": "text+file->text", + "input_modalities": [ + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, + { + "id": "openai/o3-mini-high", + "name": "OpenAI: o3 Mini High", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-02-12 15:03:31 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4, + "cache_read_input_per_million": 0.55 + } + } + }, + "metadata": { + "description": "OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...", + "architecture": { + "modality": "text+file->text", + "input_modalities": [ + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, + { + "id": "openai/o3-pro", + "name": "OpenAI: o3 Pro", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-06-10 23:32:32 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "file", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 20.0, + "output_per_million": 80.0 + } + } + }, + "metadata": { + "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "file", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, { "id": "openai/o4-mini", "name": "o4 Mini", "provider": "openrouter", "family": "o-mini", - "created_at": "2025-04-16 00:00:00 +0530", + "created_at": "2025-04-16 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 100000, "knowledge_cutoff": null, @@ -20195,18 +48639,49 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.1, "output_per_million": 4.4, - "cached_input_per_million": 0.28 + "cache_read_input_per_million": 0.28 } } }, "metadata": { + "description": "OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -20225,12 +48700,273 @@ "knowledge": "2024-06" } }, + { + "id": "openai/o4-mini-deep-research", + "name": "OpenAI: o4 Mini Deep Research", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-10-10 20:54:02 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "file", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "description": "o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.\n\nNote: This model always uses the 'web_search' tool which adds additional cost.", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "openai/o4-mini-high", + "name": "OpenAI: o4 Mini High", + "provider": "openrouter", + "family": "openai", + "created_at": "2025-04-16 17:23:32 UTC", + "context_window": 200000, + "max_output_tokens": 100000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.1, + "output_per_million": 4.4, + "cache_read_input_per_million": 0.275 + } + } + }, + "metadata": { + "description": "OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "GPT", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 100000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, + { + "id": "openrouter/auto", + "name": "Auto Router", + "provider": "openrouter", + "family": "openrouter", + "created_at": "2023-11-08 00:00:00 UTC", + "context_window": 2000000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "audio", + "file", + "video" + ], + "output": [ + "text", + "image" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": {}, + "metadata": { + "description": "\"Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...", + "architecture": { + "modality": "text+image+file+audio+video->text+image", + "input_modalities": [ + "text", + "image", + "audio", + "file", + "video" + ], + "output_modalities": [ + "text", + "image" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": null, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_completion_tokens", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "openrouter/bodybuilder", + "name": "Body Builder (beta)", + "provider": "openrouter", + "family": "openrouter", + "created_at": "2025-12-05 03:00:53 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": {}, + "metadata": { + "description": "Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": null, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [] + } + }, { "id": "openrouter/elephant-alpha", "name": "Elephant (free)", "provider": "openrouter", "family": "elephant", - "created_at": "2026-04-13 00:00:00 +0530", + "created_at": "2026-04-13 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20269,8 +49005,8 @@ "id": "openrouter/free", "name": "Free Models Router", "provider": "openrouter", - "family": null, - "created_at": "2026-02-01 00:00:00 +0530", + "family": "openrouter", + "created_at": "2026-02-01 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8000, "knowledge_cutoff": null, @@ -20287,10 +49023,48 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": {}, "metadata": { + "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": null, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -20308,12 +49082,592 @@ } } }, + { + "id": "openrouter/owl-alpha", + "name": "Owl Alpha", + "provider": "openrouter", + "family": "openrouter", + "created_at": "2026-04-28 00:00:00 UTC", + "context_window": 1048756, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "streaming", + "predicted_outputs" + ], + "pricing": {}, + "metadata": { + "description": "Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048756, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tools", + "top_k", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-30", + "status": "alpha", + "cost": { + "input": 0, + "output": 0 + }, + "limit": { + "context": 1048756, + "output": 262144 + } + } + }, + { + "id": "openrouter/pareto-code", + "name": "Pareto Code Router", + "provider": "openrouter", + "family": "openrouter", + "created_at": "2026-04-21 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 200000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "streaming" + ], + "pricing": {}, + "metadata": { + "description": "The Pareto Router is a way to have OpenRouter always pick a strong coding model for your needs without committing to a specific one. You express a single `min_coding_score` preference...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": null, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-21", + "limit": { + "context": 200000, + "output": 200000 + } + } + }, + { + "id": "perplexity/sonar", + "name": "Perplexity: Sonar", + "provider": "openrouter", + "family": "perplexity", + "created_at": "2025-01-27 21:36:48 UTC", + "context_window": 127072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.0, + "output_per_million": 1.0 + } + } + }, + "metadata": { + "description": "Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 127072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "temperature", + "top_k", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "perplexity/sonar-deep-research", + "name": "Perplexity: Sonar Deep Research", + "provider": "openrouter", + "family": "perplexity", + "created_at": "2025-03-07 01:34:06 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0, + "reasoning_output_per_million": 3.0 + } + } + }, + "metadata": { + "description": "Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": "deepseek-r1" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "temperature", + "top_k", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "perplexity/sonar-pro", + "name": "Perplexity: Sonar Pro", + "provider": "openrouter", + "family": "perplexity", + "created_at": "2025-03-07 01:53:43 UTC", + "context_window": 200000, + "max_output_tokens": 8000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 15.0 + } + } + }, + "metadata": { + "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "temperature", + "top_k", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "perplexity/sonar-pro-search", + "name": "Perplexity: Sonar Pro Search", + "provider": "openrouter", + "family": "perplexity", + "created_at": "2025-10-30 19:59:26 UTC", + "context_window": 200000, + "max_output_tokens": 8000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 15.0 + } + } + }, + "metadata": { + "description": "Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 8000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "structured_outputs", + "temperature", + "top_k", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "perplexity/sonar-reasoning-pro", + "name": "Perplexity: Sonar Reasoning Pro", + "provider": "openrouter", + "family": "perplexity", + "created_at": "2025-03-07 02:08:28 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 8.0 + } + } + }, + "metadata": { + "description": "Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": "deepseek-r1" + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "temperature", + "top_k", + "top_p", + "web_search_options" + ] + } + }, + { + "id": "poolside/laguna-m.1:free", + "name": "Laguna M.1", + "provider": "openrouter", + "family": "poolside", + "created_at": "2026-04-28 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "streaming" + ], + "pricing": {}, + "metadata": { + "description": "Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 128K...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "tool_choice", + "tools" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-28", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 0, + "output": 0, + "cache_read": 0, + "cache_write": 0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + } + }, + { + "id": "poolside/laguna-xs.2:free", + "name": "Laguna XS.2", + "provider": "openrouter", + "family": "poolside", + "created_at": "2026-04-28 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "streaming" + ], + "pricing": {}, + "metadata": { + "description": "Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "tool_choice", + "tools" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2026-04-28", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 0, + "output": 0, + "cache_read": 0, + "cache_write": 0 + }, + "limit": { + "context": 131072, + "output": 8192 + } + } + }, { "id": "prime-intellect/intellect-3", "name": "Intellect 3", "provider": "openrouter", "family": "glm", - "created_at": "2025-01-15 00:00:00 +0530", + "created_at": "2025-01-15 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -20328,7 +49682,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -20339,6 +49694,39 @@ } }, "metadata": { + "description": "INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20356,12 +49744,149 @@ "knowledge": "2024-10" } }, + { + "id": "qwen/qwen-2.5-72b-instruct", + "name": "Qwen2.5 72B Instruct", + "provider": "openrouter", + "family": "qwen", + "created_at": "2024-09-19 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.36, + "output_per_million": 0.39999999999999997 + } + } + }, + "metadata": { + "description": "Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-2.5-7b-instruct", + "name": "Qwen: Qwen2.5 7B Instruct", + "provider": "openrouter", + "family": "qwen", + "created_at": "2024-10-16 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.04, + "output_per_million": 0.09999999999999999 + } + } + }, + "metadata": { + "description": "Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "qwen/qwen-2.5-coder-32b-instruct", "name": "Qwen2.5 Coder 32B Instruct", "provider": "openrouter", "family": "qwen", - "created_at": "2024-11-11 00:00:00 +0530", + "created_at": "2024-11-11 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -20374,10 +49899,46 @@ ] }, "capabilities": [ - "structured_output" + "structured_output", + "streaming" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.66, + "output_per_million": 1.0 + } + } + }, "metadata": { + "description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20395,12 +49956,498 @@ "knowledge": "2024-10" } }, + { + "id": "qwen/qwen-3.6-27b", + "name": "Qwen3.6 27B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-04-22 00:00:00 UTC", + "context_window": 262144, + "max_output_tokens": 81920, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.195, + "output_per_million": 1.56 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-22", + "cost": { + "input": 0.195, + "output": 1.56 + }, + "limit": { + "context": 262144, + "output": 81920 + }, + "knowledge": "2025-04" + } + }, + { + "id": "qwen/qwen-max", + "name": "Qwen: Qwen-Max ", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-02-01 09:31:29 UTC", + "context_window": 32768, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.04, + "output_per_million": 4.16, + "cache_read_input_per_million": 0.20800000000000002 + } + } + }, + "metadata": { + "description": "Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-plus", + "name": "Qwen: Qwen-Plus", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-02-01 11:37:20 UTC", + "context_window": 1000000, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.26, + "output_per_million": 0.78, + "cache_read_input_per_million": 0.052000000000000005 + } + } + }, + "metadata": { + "description": "Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-plus-2025-07-28", + "name": "Qwen: Qwen Plus 0728", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-08 16:06:39 UTC", + "context_window": 1000000, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.26, + "output_per_million": 0.78 + } + } + }, + "metadata": { + "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-plus-2025-07-28:thinking", + "name": "Qwen: Qwen Plus 0728 (thinking)", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-08 16:06:39 UTC", + "context_window": 1000000, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.26, + "output_per_million": 0.78 + } + } + }, + "metadata": { + "description": "Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-turbo", + "name": "Qwen: Qwen-Turbo", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-02-01 11:56:14 UTC", + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.0325, + "output_per_million": 0.13, + "cache_read_input_per_million": 0.006500000000000001 + } + } + }, + "metadata": { + "description": "Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-vl-max", + "name": "Qwen: Qwen VL Max", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-02-01 18:25:04 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.52, + "output_per_million": 2.08 + } + } + }, + "metadata": { + "description": "Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.\n", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen-vl-plus", + "name": "Qwen: Qwen VL Plus", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-02-05 04:54:15 UTC", + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.1365, + "output_per_million": 0.40950000000000003, + "cache_read_input_per_million": 0.027299999999999998 + } + } + }, + "metadata": { + "description": "Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "top_p" + ] + } + }, { "id": "qwen/qwen2.5-vl-72b-instruct", "name": "Qwen2.5 VL 72B Instruct", "provider": "openrouter", "family": "qwen", - "created_at": "2025-02-01 00:00:00 +0530", + "created_at": "2025-02-01 00:00:00 UTC", "context_window": 32768, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -20415,10 +50462,52 @@ }, "capabilities": [ "structured_output", - "vision" + "vision", + "streaming", + "predicted_outputs" ], - "pricing": {}, + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 0.75 + } + } + }, "metadata": { + "description": "Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 32000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20436,12 +50525,148 @@ "knowledge": "2024-10" } }, + { + "id": "qwen/qwen3-14b", + "name": "Qwen: Qwen3 14B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-04-28 21:41:18 UTC", + "context_window": 40960, + "max_output_tokens": 40960, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.06, + "output_per_million": 0.24 + } + } + }, + "metadata": { + "description": "Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": "qwen3" + }, + "top_provider": { + "context_length": 40960, + "max_completion_tokens": 40960, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-235b-a22b", + "name": "Qwen: Qwen3 235B A22B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-04-28 21:29:17 UTC", + "context_window": 131072, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.45499999999999996, + "output_per_million": 1.8199999999999998 + } + } + }, + "metadata": { + "description": "Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": "qwen3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "qwen/qwen3-235b-a22b-07-25", "name": "Qwen3 235B A22B Instruct 2507", "provider": "openrouter", "family": "qwen", - "created_at": "2025-04-28 00:00:00 +0530", + "created_at": "2025-04-28 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -20483,12 +50708,83 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3-235b-a22b-2507", + "name": "Qwen: Qwen3 235B A22B Instruct 2507", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-07-21 17:39:15 UTC", + "context_window": 262144, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.071, + "output_per_million": 0.09999999999999999 + } + } + }, + "metadata": { + "description": "Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, { "id": "qwen/qwen3-235b-a22b-thinking-2507", "name": "Qwen3 235B A22B Thinking 2507", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-25 00:00:00 +0530", + "created_at": "2025-07-25 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 81920, "knowledge_cutoff": null, @@ -20503,7 +50799,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20514,6 +50812,43 @@ } }, "metadata": { + "description": "Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": "qwen3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20531,12 +50866,85 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3-30b-a3b", + "name": "Qwen: Qwen3 30B A3B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-04-28 22:16:44 UTC", + "context_window": 40960, + "max_output_tokens": 20000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09, + "output_per_million": 0.44999999999999996 + } + } + }, + "metadata": { + "description": "Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": "qwen3" + }, + "top_provider": { + "context_length": 40960, + "max_completion_tokens": 20000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, { "id": "qwen/qwen3-30b-a3b-instruct-2507", "name": "Qwen3 30B A3B Instruct 2507", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-29 00:00:00 +0530", + "created_at": "2025-07-29 00:00:00 UTC", "context_window": 262000, "max_output_tokens": 262000, "knowledge_cutoff": null, @@ -20550,7 +50958,9 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20561,6 +50971,41 @@ } }, "metadata": { + "description": "Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20583,7 +51028,7 @@ "name": "Qwen3 30B A3B Thinking 2507", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-29 00:00:00 +0530", + "created_at": "2025-07-29 00:00:00 UTC", "context_window": 262000, "max_output_tokens": 262000, "knowledge_cutoff": null, @@ -20598,7 +51043,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20609,6 +51056,43 @@ } }, "metadata": { + "description": "Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20626,12 +51110,156 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3-32b", + "name": "Qwen: Qwen3 32B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-04-28 21:32:25 UTC", + "context_window": 40960, + "max_output_tokens": 40960, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.08, + "output_per_million": 0.24, + "cache_read_input_per_million": 0.04 + } + } + }, + "metadata": { + "description": "Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": "qwen3" + }, + "top_provider": { + "context_length": 40960, + "max_completion_tokens": 40960, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-8b", + "name": "Qwen: Qwen3 8B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-04-28 21:43:52 UTC", + "context_window": 40960, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.049999999999999996, + "output_per_million": 0.39999999999999997, + "cache_read_input_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": "qwen3" + }, + "top_provider": { + "context_length": 40960, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "qwen/qwen3-coder", "name": "Qwen3 Coder", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-23 00:00:00 +0530", + "created_at": "2025-07-23 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 66536, "knowledge_cutoff": null, @@ -20645,7 +51273,9 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20656,6 +51286,41 @@ } }, "metadata": { + "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20678,7 +51343,7 @@ "name": "Qwen3 Coder 30B A3B Instruct", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-31 00:00:00 +0530", + "created_at": "2025-07-31 00:00:00 UTC", "context_window": 160000, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -20692,7 +51357,8 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { @@ -20703,6 +51369,39 @@ } }, "metadata": { + "description": "Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 160000, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20725,7 +51424,7 @@ "name": "Qwen3 Coder Flash", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-23 00:00:00 +0530", + "created_at": "2025-07-23 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 66536, "knowledge_cutoff": null, @@ -20738,7 +51437,9 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { @@ -20749,6 +51450,34 @@ } }, "metadata": { + "description": "Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -20766,12 +51495,145 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3-coder-next", + "name": "Qwen: Qwen3 Coder Next", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-02-04 00:15:01 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.11, + "output_per_million": 0.7999999999999999, + "cache_read_input_per_million": 0.07 + } + } + }, + "metadata": { + "description": "Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-coder-plus", + "name": "Qwen: Qwen3 Coder Plus", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-23 21:25:07 UTC", + "context_window": 1000000, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.65, + "output_per_million": 3.25, + "cache_read_input_per_million": 0.13 + } + } + }, + "metadata": { + "description": "Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, { "id": "qwen/qwen3-coder:exacto", "name": "Qwen3 Coder (exacto)", "provider": "openrouter", "family": "qwen", - "created_at": "2025-07-23 00:00:00 +0530", + "created_at": "2025-07-23 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20813,12 +51675,66 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3-coder:free", + "name": "Qwen: Qwen3 Coder 480B A35B (free)", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-07-23 00:29:06 UTC", + "context_window": 262000, + "max_output_tokens": 262000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "description": "Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262000, + "max_completion_tokens": 262000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "qwen/qwen3-max", "name": "Qwen3 Max", "provider": "openrouter", "family": "qwen", - "created_at": "2025-09-05 00:00:00 +0530", + "created_at": "2025-09-05 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -20832,7 +51748,9 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { @@ -20843,6 +51761,34 @@ } }, "metadata": { + "description": "Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -20860,13 +51806,13 @@ } }, { - "id": "qwen/qwen3-next-80b-a3b-instruct", - "name": "Qwen3 Next 80B A3B Instruct", + "id": "qwen/qwen3-max-thinking", + "name": "Qwen: Qwen3 Max Thinking", "provider": "openrouter", "family": "qwen", - "created_at": "2025-09-11 00:00:00 +0530", + "created_at": "2026-02-09 21:18:21 UTC", "context_window": 262144, - "max_output_tokens": 262144, + "max_output_tokens": 32768, "knowledge_cutoff": null, "modalities": { "input": [ @@ -20877,41 +51823,58 @@ ] }, "capabilities": [ + "streaming", "function_calling", "structured_output" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.14, - "output_per_million": 1.4 + "input_per_million": 0.78, + "output_per_million": 3.9 } } }, "metadata": { - "source": "models.dev", - "provider_id": "openrouter", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2025-09-11", - "cost": { - "input": 0.14, - "output": 1.4 + "description": "Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null }, - "limit": { - "context": 262144, - "output": 262144 + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 32768, + "is_moderated": false }, - "knowledge": "2025-04" + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] } }, { - "id": "qwen/qwen3-next-80b-a3b-thinking", - "name": "Qwen3 Next 80B A3B Thinking", + "id": "qwen/qwen3-next-80b-a3b-instruct", + "name": "Qwen3 Next 80B A3B Instruct", "provider": "openrouter", "family": "qwen", - "created_at": "2025-09-11 00:00:00 +0530", + "created_at": "2025-09-11 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 262144, "knowledge_cutoff": null, @@ -20926,7 +51889,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20937,6 +51901,41 @@ } }, "metadata": { + "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -20954,12 +51953,870 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3-next-80b-a3b-instruct:free", + "name": "Qwen: Qwen3 Next 80B A3B Instruct (free)", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-11 17:36:53 UTC", + "context_window": 262144, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "description": "Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-next-80b-a3b-thinking", + "name": "Qwen3 Next 80B A3B Thinking", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-11 00:00:00 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.14, + "output_per_million": 1.4 + } + } + }, + "metadata": { + "description": "Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": false, + "temperature": true, + "last_updated": "2025-09-11", + "cost": { + "input": 0.14, + "output": 1.4 + }, + "limit": { + "context": 262144, + "output": 262144 + }, + "knowledge": "2025-04" + } + }, + { + "id": "qwen/qwen3-vl-235b-a22b-instruct", + "name": "Qwen: Qwen3 VL 235B A22B Instruct", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-23 23:04:47 UTC", + "context_window": 262144, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.19999999999999998, + "output_per_million": 0.88, + "cache_read_input_per_million": 0.11 + } + } + }, + "metadata": { + "description": "Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-vl-235b-a22b-thinking", + "name": "Qwen: Qwen3 VL 235B A22B Thinking", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-09-23 23:04:50 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.26, + "output_per_million": 2.6 + } + } + }, + "metadata": { + "description": "Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-vl-30b-a3b-instruct", + "name": "Qwen: Qwen3 VL 30B A3B Instruct", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-10-06 23:47:56 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.13, + "output_per_million": 0.52 + } + } + }, + "metadata": { + "description": "Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-vl-30b-a3b-thinking", + "name": "Qwen: Qwen3 VL 30B A3B Thinking", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-10-06 23:47:59 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.13, + "output_per_million": 1.56 + } + } + }, + "metadata": { + "description": "Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-vl-32b-instruct", + "name": "Qwen: Qwen3 VL 32B Instruct", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-10-23 14:55:32 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.10400000000000001, + "output_per_million": 0.41600000000000004 + } + } + }, + "metadata": { + "description": "Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-vl-8b-instruct", + "name": "Qwen: Qwen3 VL 8B Instruct", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-10-14 17:35:08 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.08, + "output_per_million": 0.5 + } + } + }, + "metadata": { + "description": "Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3-vl-8b-thinking", + "name": "Qwen: Qwen3 VL 8B Thinking", + "provider": "openrouter", + "family": "qwen", + "created_at": "2025-10-14 17:42:26 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.117, + "output_per_million": 1.365 + } + } + }, + "metadata": { + "description": "Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.5-122b-a10b", + "name": "Qwen: Qwen3.5-122B-A10B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-02-25 21:09:49 UTC", + "context_window": 262144, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.26, + "output_per_million": 2.08 + } + } + }, + "metadata": { + "description": "The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.5-27b", + "name": "Qwen: Qwen3.5-27B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-02-25 21:10:10 UTC", + "context_window": 262144, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.195, + "output_per_million": 1.56 + } + } + }, + "metadata": { + "description": "The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.5-35b-a3b", + "name": "Qwen: Qwen3.5-35B-A3B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-02-25 21:10:22 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 1.0, + "cache_read_input_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, { "id": "qwen/qwen3.5-397b-a17b", "name": "Qwen3.5 397B A17B", "provider": "openrouter", "family": "qwen", - "created_at": "2026-02-16 00:00:00 +0530", + "created_at": "2026-02-16 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -20977,7 +52834,9 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -20988,6 +52847,47 @@ } }, "metadata": { + "description": "The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -21005,12 +52905,88 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3.5-9b", + "name": "Qwen: Qwen3.5-9B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-03-10 14:19:56 UTC", + "context_window": 262144, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.15 + } + } + }, + "metadata": { + "description": "Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, { "id": "qwen/qwen3.5-flash-02-23", "name": "Qwen: Qwen3.5-Flash", "provider": "openrouter", "family": "qwen", - "created_at": "2026-02-25 00:00:00 +0530", + "created_at": "2026-02-25 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -21028,7 +53004,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -21039,6 +53016,39 @@ } }, "metadata": { + "description": "The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21060,7 +53070,7 @@ "name": "Qwen3.5 Plus 2026-02-15", "provider": "openrouter", "family": "qwen", - "created_at": "2026-02-16 00:00:00 +0530", + "created_at": "2026-02-16 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -21078,7 +53088,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -21089,6 +53100,39 @@ } }, "metadata": { + "description": "The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21106,12 +53150,367 @@ "knowledge": "2025-04" } }, + { + "id": "qwen/qwen3.5-plus-20260420", + "name": "Qwen: Qwen3.5 Plus 2026-04-20", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-04-27 03:42:48 UTC", + "context_window": 1000000, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.39999999999999997, + "output_per_million": 2.4 + } + } + }, + "metadata": { + "description": "Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.6-27b", + "name": "Qwen: Qwen3.6 27B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-04-27 01:57:44 UTC", + "context_window": 262144, + "max_output_tokens": 81920, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.32, + "output_per_million": 3.1999999999999997 + } + } + }, + "metadata": { + "description": "Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 81920, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.6-35b-a3b", + "name": "Qwen: Qwen3.6 35B A3B", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-04-27 03:24:15 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 1.0, + "cache_read_input_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.6-flash", + "name": "Qwen: Qwen3.6 Flash", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-04-27 03:42:42 UTC", + "context_window": 1000000, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 1.5 + } + } + }, + "metadata": { + "description": "Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "qwen/qwen3.6-max-preview", + "name": "Qwen: Qwen3.6 Max Preview", + "provider": "openrouter", + "family": "qwen", + "created_at": "2026-04-27 03:24:02 UTC", + "context_window": 262144, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.04, + "output_per_million": 6.24 + } + } + }, + "metadata": { + "description": "Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, { "id": "qwen/qwen3.6-plus", "name": "Qwen3.6 Plus", "provider": "openrouter", "family": "qwen", - "created_at": "2026-04-02 00:00:00 +0530", + "created_at": "2026-04-02 00:00:00 UTC", "context_window": 1000000, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -21129,7 +53528,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -21140,6 +53540,39 @@ } }, "metadata": { + "description": "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "text", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen3", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21157,12 +53590,582 @@ "knowledge": "2025-04" } }, + { + "id": "rekaai/reka-edge", + "name": "Reka Edge", + "provider": "openrouter", + "family": "rekaai", + "created_at": "2026-03-20 17:16:05 UTC", + "context_window": 16384, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.09999999999999999 + } + } + }, + "metadata": { + "description": "Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 16384, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "rekaai/reka-flash-3", + "name": "Reka Flash 3", + "provider": "openrouter", + "family": "rekaai", + "created_at": "2025-03-12 20:53:33 UTC", + "context_window": 65536, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "relace/relace-apply-3", + "name": "Relace: Relace Apply 3", + "provider": "openrouter", + "family": "relace", + "created_at": "2025-09-26 12:59:32 UTC", + "context_window": 256000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.85, + "output_per_million": 1.25 + } + } + }, + "metadata": { + "description": "Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "seed", + "stop" + ] + } + }, + { + "id": "relace/relace-search", + "name": "Relace: Relace Search", + "provider": "openrouter", + "family": "relace", + "created_at": "2025-12-08 17:06:00 UTC", + "context_window": 256000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.0, + "output_per_million": 3.0 + } + } + }, + "metadata": { + "description": "The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "sao10k/l3-euryale-70b", + "name": "Sao10k: Llama 3 Euryale 70B v2.1", + "provider": "openrouter", + "family": "sao10k", + "created_at": "2024-06-18 00:00:00 UTC", + "context_window": 8192, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.48, + "output_per_million": 1.48 + } + } + }, + "metadata": { + "description": "Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique and custom...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 8192, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "sao10k/l3-lunaris-8b", + "name": "Sao10K: Llama 3 8B Lunaris", + "provider": "openrouter", + "family": "sao10k", + "created_at": "2024-08-13 00:00:00 UTC", + "context_window": 8192, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.04, + "output_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 8192, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "sao10k/l3.1-70b-hanami-x1", + "name": "Sao10K: Llama 3.1 70B Hanami x1", + "provider": "openrouter", + "family": "sao10k", + "created_at": "2025-01-08 02:20:54 UTC", + "context_window": 16000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 3.0 + } + } + }, + "metadata": { + "description": "This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": null + }, + "top_provider": { + "context_length": 16000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "sao10k/l3.1-euryale-70b", + "name": "Sao10K: Llama 3.1 Euryale 70B v2.2", + "provider": "openrouter", + "family": "sao10k", + "created_at": "2024-08-28 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.85, + "output_per_million": 0.85 + } + } + }, + "metadata": { + "description": "Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "sao10k/l3.3-euryale-70b", + "name": "Sao10K: Llama 3.3 Euryale 70B", + "provider": "openrouter", + "family": "sao10k", + "created_at": "2024-12-18 15:32:08 UTC", + "context_window": 131072, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.65, + "output_per_million": 0.75 + } + } + }, + "metadata": { + "description": "Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama3", + "instruct_type": "llama3" + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, { "id": "sourceful/riverflow-v2-fast-preview", "name": "Riverflow V2 Fast Preview", "provider": "openrouter", "family": "sourceful", - "created_at": "2025-12-08 00:00:00 +0530", + "created_at": "2025-12-08 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21202,7 +54205,7 @@ "name": "Riverflow V2 Max Preview", "provider": "openrouter", "family": "sourceful", - "created_at": "2025-12-08 00:00:00 +0530", + "created_at": "2025-12-08 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21242,7 +54245,7 @@ "name": "Riverflow V2 Standard Preview", "provider": "openrouter", "family": "sourceful", - "created_at": "2025-12-08 00:00:00 +0530", + "created_at": "2025-12-08 00:00:00 UTC", "context_window": 8192, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21282,7 +54285,7 @@ "name": "Step 3.5 Flash", "provider": "openrouter", "family": "step", - "created_at": "2026-01-29 00:00:00 +0530", + "created_at": "2026-01-29 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 256000, "knowledge_cutoff": null, @@ -21296,18 +54299,57 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.3, - "cached_input_per_million": 0.02 + "cache_read_input_per_million": 0.02 } } }, "metadata": { + "description": "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -21326,12 +54368,708 @@ "knowledge": "2025-01" } }, + { + "id": "switchpoint/router", + "name": "Switchpoint Router", + "provider": "openrouter", + "family": "switchpoint", + "created_at": "2025-07-11 22:28:19 UTC", + "context_window": 131072, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.85, + "output_per_million": 3.4 + } + } + }, + "metadata": { + "description": "Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "tencent/hunyuan-a13b-instruct", + "name": "Tencent: Hunyuan A13B Instruct", + "provider": "openrouter", + "family": "tencent", + "created_at": "2025-07-08 15:14:24 UTC", + "context_window": 131072, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.14, + "output_per_million": 0.5700000000000001 + } + } + }, + "metadata": { + "description": "Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "structured_outputs", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "tencent/hy3-preview:free", + "name": "Tencent: Hy3 preview (free)", + "provider": "openrouter", + "family": "tencent", + "created_at": "2026-04-22 17:15:50 UTC", + "context_window": 262144, + "max_output_tokens": 262144, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 262144, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "thedrummer/cydonia-24b-v4.1", + "name": "TheDrummer: Cydonia 24B V4.1", + "provider": "openrouter", + "family": "thedrummer", + "created_at": "2025-09-27 00:11:18 UTC", + "context_window": 131072, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 0.5, + "cache_read_input_per_million": 0.15 + } + } + }, + "metadata": { + "description": "Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "thedrummer/rocinante-12b", + "name": "TheDrummer: Rocinante 12B", + "provider": "openrouter", + "family": "thedrummer", + "created_at": "2024-09-30 00:00:00 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.16999999999999998, + "output_per_million": 0.43 + } + } + }, + "metadata": { + "description": "Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Qwen", + "instruct_type": "chatml" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "thedrummer/skyfall-36b-v2", + "name": "TheDrummer: Skyfall 36B V2", + "provider": "openrouter", + "family": "thedrummer", + "created_at": "2025-03-10 19:56:06 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.55, + "output_per_million": 0.7999999999999999, + "cache_read_input_per_million": 0.25 + } + } + }, + "metadata": { + "description": "Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "seed", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, + { + "id": "thedrummer/unslopnemo-12b", + "name": "TheDrummer: UnslopNemo 12B", + "provider": "openrouter", + "family": "thedrummer", + "created_at": "2024-11-08 22:04:08 UTC", + "context_window": 32768, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.39999999999999997, + "output_per_million": 0.39999999999999997 + } + } + }, + "metadata": { + "description": "UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Mistral", + "instruct_type": "mistral" + }, + "top_provider": { + "context_length": 32768, + "max_completion_tokens": 32768, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "tngtech/deepseek-r1t2-chimera", + "name": "TNG: DeepSeek R1T2 Chimera", + "provider": "openrouter", + "family": "tngtech", + "created_at": "2025-07-08 15:03:05 UTC", + "context_window": 163840, + "max_output_tokens": 163840, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 1.1, + "cache_read_input_per_million": 0.15 + } + } + }, + "metadata": { + "description": "DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "DeepSeek", + "instruct_type": null + }, + "top_provider": { + "context_length": 163840, + "max_completion_tokens": 163840, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "undi95/remm-slerp-l2-13b", + "name": "ReMM SLERP 13B", + "provider": "openrouter", + "family": "undi95", + "created_at": "2023-07-22 00:00:00 UTC", + "context_window": 6144, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.44999999999999996, + "output_per_million": 0.65 + } + } + }, + "metadata": { + "description": "A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Llama2", + "instruct_type": "alpaca" + }, + "top_provider": { + "context_length": 6144, + "max_completion_tokens": 4096, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "top_a", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "upstage/solar-pro-3", + "name": "Upstage: Solar Pro 3", + "provider": "openrouter", + "family": "upstage", + "created_at": "2026-01-27 02:33:20 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.15, + "output_per_million": 0.6, + "cache_read_input_per_million": 0.015 + } + } + }, + "metadata": { + "description": "Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "structured_outputs", + "temperature", + "tool_choice", + "tools" + ] + } + }, + { + "id": "writer/palmyra-x5", + "name": "Writer: Palmyra X5", + "provider": "openrouter", + "family": "writer", + "created_at": "2026-01-21 13:57:03 UTC", + "context_window": 1040000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.6, + "output_per_million": 6.0 + } + } + }, + "metadata": { + "description": "Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1040000, + "max_completion_tokens": 8192, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "stop", + "temperature", + "top_k", + "top_p" + ] + } + }, { "id": "x-ai/grok-3", "name": "Grok 3", "provider": "openrouter", "family": "grok", - "created_at": "2025-02-17 00:00:00 +0530", + "created_at": "2025-02-17 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21345,18 +55083,53 @@ }, "capabilities": [ "function_calling", - "structured_output" + "structured_output", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.75 + "cache_read_input_per_million": 0.75, + "cache_write_input_per_million": 15 } } }, "metadata": { + "description": "Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21381,7 +55154,7 @@ "name": "Grok 3 Beta", "provider": "openrouter", "family": "grok", - "created_at": "2025-02-17 00:00:00 +0530", + "created_at": "2025-02-17 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21394,18 +55167,53 @@ ] }, "capabilities": [ - "function_calling" + "function_calling", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.75 + "cache_read_input_per_million": 0.75, + "cache_write_input_per_million": 15 } } }, "metadata": { + "description": "Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "logprobs", + "max_tokens", + "presence_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21430,7 +55238,7 @@ "name": "Grok 3 Mini", "provider": "openrouter", "family": "grok", - "created_at": "2025-02-17 00:00:00 +0530", + "created_at": "2025-02-17 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21445,18 +55253,53 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 0.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075, + "cache_write_input_per_million": 0.5 } } }, "metadata": { + "description": "A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21481,7 +55324,7 @@ "name": "Grok 3 Mini Beta", "provider": "openrouter", "family": "grok", - "created_at": "2025-02-17 00:00:00 +0530", + "created_at": "2025-02-17 00:00:00 UTC", "context_window": 131072, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -21495,18 +55338,53 @@ }, "capabilities": [ "function_calling", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 0.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075, + "cache_write_input_per_million": 0.5 } } }, "metadata": { + "description": "Grok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21531,7 +55409,7 @@ "name": "Grok 4", "provider": "openrouter", "family": "grok", - "created_at": "2025-07-09 00:00:00 +0530", + "created_at": "2025-07-09 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 64000, "knowledge_cutoff": null, @@ -21546,18 +55424,54 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 3, "output_per_million": 15, - "cached_input_per_million": 0.75 + "cache_read_input_per_million": 0.75, + "cache_write_input_per_million": 15 } } }, "metadata": { + "description": "Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "image", + "text", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21582,7 +55496,7 @@ "name": "Grok 4 Fast", "provider": "openrouter", "family": "grok", - "created_at": "2025-08-19 00:00:00 +0530", + "created_at": "2025-08-19 00:00:00 UTC", "context_window": 2000000, "max_output_tokens": 30000, "knowledge_cutoff": null, @@ -21599,18 +55513,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.2, "output_per_million": 0.5, - "cached_input_per_million": 0.05 + "cache_read_input_per_million": 0.05, + "cache_write_input_per_million": 0.05 } } }, "metadata": { + "description": "Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 2000000, + "max_completion_tokens": 30000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21635,7 +55585,7 @@ "name": "Grok 4.1 Fast", "provider": "openrouter", "family": "grok", - "created_at": "2025-11-19 00:00:00 +0530", + "created_at": "2025-11-19 00:00:00 UTC", "context_window": 2000000, "max_output_tokens": 30000, "knowledge_cutoff": null, @@ -21652,18 +55602,54 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.2, "output_per_million": 0.5, - "cached_input_per_million": 0.05 + "cache_read_input_per_million": 0.05, + "cache_write_input_per_million": 0.05 } } }, "metadata": { + "description": "Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disabled using...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 2000000, + "max_completion_tokens": 30000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21683,12 +55669,82 @@ "knowledge": "2024-11" } }, + { + "id": "x-ai/grok-4.20", + "name": "xAI: Grok 4.20", + "provider": "openrouter", + "family": "x-ai", + "created_at": "2026-03-31 17:43:39 UTC", + "context_window": 2000000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 2.5, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 2000000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ] + } + }, { "id": "x-ai/grok-4.20-beta", "name": "Grok 4.20 Beta", "provider": "openrouter", "family": "grok", - "created_at": "2026-03-12 00:00:00 +0530", + "created_at": "2026-03-12 00:00:00 UTC", "context_window": 2000000, "max_output_tokens": 30000, "knowledge_cutoff": null, @@ -21711,7 +55767,7 @@ "standard": { "input_per_million": 2, "output_per_million": 6, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, @@ -21738,12 +55794,79 @@ } } }, + { + "id": "x-ai/grok-4.20-multi-agent", + "name": "xAI: Grok 4.20 Multi-Agent", + "provider": "openrouter", + "family": "x-ai", + "created_at": "2026-03-31 17:45:58 UTC", + "context_window": 2000000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 6.0, + "cache_read_input_per_million": 0.19999999999999998 + } + } + }, + "metadata": { + "description": "Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "text", + "image", + "file" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 2000000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "temperature", + "top_logprobs", + "top_p" + ] + } + }, { "id": "x-ai/grok-4.20-multi-agent-beta", "name": "Grok 4.20 Multi - Agent Beta", "provider": "openrouter", "family": "grok", - "created_at": "2026-03-12 00:00:00 +0530", + "created_at": "2026-03-12 00:00:00 UTC", "context_window": 2000000, "max_output_tokens": 30000, "knowledge_cutoff": null, @@ -21765,7 +55888,7 @@ "standard": { "input_per_million": 2, "output_per_million": 6, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, @@ -21792,12 +55915,105 @@ } } }, + { + "id": "x-ai/grok-4.3", + "name": "Grok 4.3", + "provider": "openrouter", + "family": "grok", + "created_at": "2026-05-01 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 1000000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 2.5, + "cache_read_input_per_million": 0.2 + } + } + }, + "metadata": { + "description": "Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logprobs", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-05-01", + "cost": { + "input": 1.25, + "output": 2.5, + "cache_read": 0.2, + "context_over_200k": { + "input": 2.5, + "output": 5, + "cache_read": 0.4 + } + }, + "limit": { + "context": 1000000, + "output": 1000000 + } + } + }, { "id": "x-ai/grok-code-fast-1", "name": "Grok Code Fast 1", "provider": "openrouter", "family": "grok", - "created_at": "2025-08-26 00:00:00 +0530", + "created_at": "2025-08-26 00:00:00 UTC", "context_window": 256000, "max_output_tokens": 10000, "knowledge_cutoff": null, @@ -21812,18 +56028,52 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.2, "output_per_million": 1.5, - "cached_input_per_million": 0.02 + "cache_read_input_per_million": 0.02 } } }, "metadata": { + "description": "Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Grok", + "instruct_type": null + }, + "top_provider": { + "context_length": 256000, + "max_completion_tokens": 10000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "logprobs", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -21844,13 +56094,13 @@ }, { "id": "xiaomi/mimo-v2-flash", - "name": "MiMo-V2-Flash", + "name": "Xiaomi: MiMo-V2-Flash", "provider": "openrouter", "family": "mimo", - "created_at": "2025-12-14 00:00:00 +0530", + "created_at": "2025-12-16 00:00:00 UTC", "context_window": 262144, "max_output_tokens": 65536, - "knowledge_cutoff": null, + "knowledge_cutoff": "2024-12-01", "modalities": { "input": [ "text" @@ -21861,25 +56111,64 @@ }, "capabilities": [ "function_calling", - "structured_output", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.3, - "cached_input_per_million": 0.01 + "cache_read_input_per_million": 0.01 } } }, "metadata": { + "description": "MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, "attachment": false, "temperature": true, - "last_updated": "2025-12-14", + "last_updated": "2026-02-04", + "interleaved": { + "field": "reasoning_details" + }, "cost": { "input": 0.1, "output": 0.3, @@ -21889,24 +56178,25 @@ "context": 262144, "output": 65536 }, - "knowledge": "2024-12" + "knowledge": "2024-12-01" } }, { "id": "xiaomi/mimo-v2-omni", - "name": "MiMo-V2-Omni", + "name": "Xiaomi: MiMo-V2-Omni", "provider": "openrouter", "family": "mimo", - "created_at": "2026-03-18 00:00:00 +0530", + "created_at": "2026-03-18 00:00:00 UTC", "context_window": 262144, - "max_output_tokens": 65536, + "max_output_tokens": 131072, "knowledge_cutoff": null, "modalities": { "input": [ "text", "image", + "audio", "video", - "audio" + "pdf" ], "output": [ "text" @@ -21914,23 +56204,58 @@ }, "capabilities": [ "function_calling", - "structured_output", "reasoning", - "vision" + "vision", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.4, "output_per_million": 2, - "cached_input_per_million": 0.08 + "cache_read_input_per_million": 0.08 } } }, "metadata": { + "description": "MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step...", + "architecture": { + "modality": "text+image+audio+video->text", + "input_modalities": [ + "text", + "audio", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", - "open_weights": true, + "open_weights": false, "attachment": true, "temperature": true, "last_updated": "2026-03-18", @@ -21944,18 +56269,19 @@ }, "limit": { "context": 262144, - "output": 65536 - } + "output": 131072 + }, + "knowledge": "2024-12" } }, { "id": "xiaomi/mimo-v2-pro", - "name": "MiMo-V2-Pro", + "name": "Xiaomi: MiMo-V2-Pro", "provider": "openrouter", "family": "mimo", - "created_at": "2026-03-18 00:00:00 +0530", + "created_at": "2026-03-18 00:00:00 UTC", "context_window": 1048576, - "max_output_tokens": 65536, + "max_output_tokens": 131072, "knowledge_cutoff": null, "modalities": { "input": [ @@ -21967,23 +56293,55 @@ }, "capabilities": [ "function_calling", - "structured_output", - "reasoning" + "reasoning", + "streaming", + "structured_output" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1, "output_per_million": 3, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, "metadata": { + "description": "MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent frameworks like...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", - "open_weights": true, - "attachment": false, + "open_weights": false, + "attachment": true, "temperature": true, "last_updated": "2026-03-18", "interleaved": { @@ -21992,12 +56350,262 @@ "cost": { "input": 1, "output": 3, - "cache_read": 0.2 + "cache_read": 0.2, + "context_over_200k": { + "input": 2, + "output": 6, + "cache_read": 0.4 + } }, "limit": { "context": 1048576, - "output": 65536 + "output": 131072 + }, + "knowledge": "2024-12" + } + }, + { + "id": "xiaomi/mimo-v2.5", + "name": "Xiaomi: MiMo-V2.5", + "provider": "openrouter", + "family": "mimo", + "created_at": "2026-04-22 00:00:00 UTC", + "context_window": 1048576, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision", + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.4, + "output_per_million": 2, + "cache_read_input_per_million": 0.08 + } } + }, + "metadata": { + "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...", + "architecture": { + "modality": "text+image+audio+video->text", + "input_modalities": [ + "text", + "audio", + "image", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-22", + "interleaved": { + "field": "reasoning_details" + }, + "cost": { + "input": 0.4, + "output": 2, + "cache_read": 0.08, + "context_over_200k": { + "input": 0.8, + "output": 4, + "cache_read": 0.16 + } + }, + "limit": { + "context": 1048576, + "output": 131072 + }, + "knowledge": "2024-12" + } + }, + { + "id": "xiaomi/mimo-v2.5-pro", + "name": "Xiaomi: MiMo-V2.5-Pro", + "provider": "openrouter", + "family": "mimo", + "created_at": "2026-04-22 00:00:00 UTC", + "context_window": 1048576, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "streaming", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1, + "output_per_million": 3, + "cache_read_input_per_million": 0.2 + } + } + }, + "metadata": { + "description": "MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "response_format", + "stop", + "temperature", + "tool_choice", + "tools", + "top_p" + ], + "source": "models.dev", + "provider_id": "openrouter", + "open_weights": true, + "attachment": true, + "temperature": true, + "last_updated": "2026-04-22", + "interleaved": { + "field": "reasoning_content" + }, + "cost": { + "input": 1, + "output": 3, + "cache_read": 0.2, + "context_over_200k": { + "input": 2, + "output": 6, + "cache_read": 0.4 + } + }, + "limit": { + "context": 1048576, + "output": 131072 + }, + "knowledge": "2024-12" + } + }, + { + "id": "z-ai/glm-4-32b", + "name": "Z.ai: GLM 4 32B ", + "provider": "openrouter", + "family": "z-ai", + "created_at": "2025-07-24 17:03:37 UTC", + "context_window": 128000, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.09999999999999999, + "output_per_million": 0.09999999999999999 + } + } + }, + "metadata": { + "description": "GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks. It...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 128000, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "max_tokens", + "temperature", + "tool_choice", + "tools", + "top_p" + ] } }, { @@ -22005,7 +56613,7 @@ "name": "GLM 4.5", "provider": "openrouter", "family": "glm", - "created_at": "2025-07-28 00:00:00 +0530", + "created_at": "2025-07-28 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 96000, "knowledge_cutoff": null, @@ -22020,7 +56628,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -22031,6 +56640,40 @@ } }, "metadata": { + "description": "GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 98304, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22053,7 +56696,7 @@ "name": "GLM 4.5 Air", "provider": "openrouter", "family": "glm-air", - "created_at": "2025-07-28 00:00:00 +0530", + "created_at": "2025-07-28 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 96000, "knowledge_cutoff": null, @@ -22068,7 +56711,8 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming" ], "pricing": { "text_tokens": { @@ -22079,6 +56723,39 @@ } }, "metadata": { + "description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 98304, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22101,7 +56778,7 @@ "name": "GLM 4.5 Air (free)", "provider": "openrouter", "family": "glm-air", - "created_at": "2025-07-28 00:00:00 +0530", + "created_at": "2025-07-28 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 96000, "knowledge_cutoff": null, @@ -22114,10 +56791,39 @@ ] }, "capabilities": [ - "reasoning" + "reasoning", + "streaming", + "function_calling" ], "pricing": {}, "metadata": { + "description": "GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 96000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "temperature", + "tool_choice", + "tools", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22140,7 +56846,7 @@ "name": "GLM 4.5V", "provider": "openrouter", "family": "glm", - "created_at": "2025-08-11 00:00:00 +0530", + "created_at": "2025-08-11 00:00:00 UTC", "context_window": 64000, "max_output_tokens": 16384, "knowledge_cutoff": null, @@ -22158,7 +56864,8 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { @@ -22169,6 +56876,40 @@ } }, "metadata": { + "description": "GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 65536, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22191,7 +56932,7 @@ "name": "GLM 4.6", "provider": "openrouter", "family": "glm", - "created_at": "2025-09-30 00:00:00 +0530", + "created_at": "2025-09-30 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -22206,18 +56947,57 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.6, "output_per_million": 2.2, - "cached_input_per_million": 0.11 + "cache_read_input_per_million": 0.11 } } }, "metadata": { + "description": "Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 204800, + "max_completion_tokens": 204800, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22241,7 +57021,7 @@ "name": "GLM 4.6 (exacto)", "provider": "openrouter", "family": "glm", - "created_at": "2025-09-30 00:00:00 +0530", + "created_at": "2025-09-30 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 128000, "knowledge_cutoff": null, @@ -22263,7 +57043,7 @@ "standard": { "input_per_million": 0.6, "output_per_million": 1.9, - "cached_input_per_million": 0.11 + "cache_read_input_per_million": 0.11 } } }, @@ -22286,12 +57066,82 @@ "knowledge": "2025-09" } }, + { + "id": "z-ai/glm-4.6v", + "name": "Z.ai: GLM 4.6V", + "provider": "openrouter", + "family": "z-ai", + "created_at": "2025-12-08 15:24:22 UTC", + "context_window": 131072, + "max_output_tokens": 24000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.3, + "output_per_million": 0.8999999999999999, + "cache_read_input_per_million": 0.049999999999999996 + } + } + }, + "metadata": { + "description": "GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 131072, + "max_completion_tokens": 24000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "max_tokens", + "presence_penalty", + "reasoning", + "repetition_penalty", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, { "id": "z-ai/glm-4.7", "name": "GLM-4.7", "provider": "openrouter", "family": "glm", - "created_at": "2025-12-22 00:00:00 +0530", + "created_at": "2025-12-22 00:00:00 UTC", "context_window": 204800, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -22306,18 +57156,59 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.6, "output_per_million": 2.2, - "cached_input_per_million": 0.11 + "cache_read_input_per_million": 0.11 } } }, "metadata": { + "description": "GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 202752, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22344,7 +57235,7 @@ "name": "GLM-4.7-Flash", "provider": "openrouter", "family": "glm", - "created_at": "2026-01-19 00:00:00 +0530", + "created_at": "2026-01-19 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 65535, "knowledge_cutoff": null, @@ -22359,7 +57250,9 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { @@ -22370,6 +57263,43 @@ } }, "metadata": { + "description": "As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 202752, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22394,7 +57324,7 @@ "name": "GLM-5", "provider": "openrouter", "family": "glm", - "created_at": "2026-02-12 00:00:00 +0530", + "created_at": "2026-02-12 00:00:00 UTC", "context_window": 202752, "max_output_tokens": 131000, "knowledge_cutoff": null, @@ -22409,18 +57339,59 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1, "output_per_million": 3.2, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, "metadata": { + "description": "GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 202752, + "max_completion_tokens": null, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22446,7 +57417,7 @@ "name": "GLM-5-Turbo", "provider": "openrouter", "family": "glm", - "created_at": "2026-03-16 00:00:00 +0530", + "created_at": "2026-03-16 00:00:00 UTC", "context_window": 202752, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -22461,18 +57432,56 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.96, "output_per_million": 3.2, - "cached_input_per_million": 0.192 + "cache_read_input_per_million": 0.192 } } }, "metadata": { + "description": "GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 202752, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "max_tokens", + "min_p", + "presence_penalty", + "reasoning", + "repetition_penalty", + "response_format", + "seed", + "stop", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": false, @@ -22499,7 +57508,7 @@ "name": "GLM-5.1", "provider": "openrouter", "family": "glm", - "created_at": "2026-04-07 00:00:00 +0530", + "created_at": "2026-04-07 00:00:00 UTC", "context_window": 202752, "max_output_tokens": 131072, "knowledge_cutoff": null, @@ -22514,18 +57523,61 @@ "capabilities": [ "function_calling", "structured_output", - "reasoning" + "reasoning", + "streaming", + "predicted_outputs" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.4, "output_per_million": 4.4, - "cached_input_per_million": 0.26 + "cache_read_input_per_million": 0.26 } } }, "metadata": { + "description": "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...", + "architecture": { + "modality": "text->text", + "input_modalities": [ + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 202752, + "max_completion_tokens": 65535, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ], "source": "models.dev", "provider_id": "openrouter", "open_weights": true, @@ -22546,12 +57598,639 @@ } } }, + { + "id": "z-ai/glm-5v-turbo", + "name": "Z.ai: GLM 5V Turbo", + "provider": "openrouter", + "family": "z-ai", + "created_at": "2026-04-01 16:37:38 UTC", + "context_window": 202752, + "max_output_tokens": 131072, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.2, + "output_per_million": 4.0, + "cache_read_input_per_million": 0.24 + } + } + }, + "metadata": { + "description": "GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...", + "architecture": { + "modality": "text+image+video->text", + "input_modalities": [ + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Other", + "instruct_type": null + }, + "top_provider": { + "context_length": 202752, + "max_completion_tokens": 131072, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "~anthropic/claude-haiku-latest", + "name": "Anthropic Claude Haiku Latest", + "provider": "openrouter", + "family": "~anthropic", + "created_at": "2026-04-27 19:34:52 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.0, + "output_per_million": 5.0, + "cache_read_input_per_million": 0.09999999999999999 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the Anthropic Claude Haiku family.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 200000, + "max_completion_tokens": 64000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p" + ] + } + }, + { + "id": "~anthropic/claude-opus-latest", + "name": "Anthropic: Claude Opus Latest", + "provider": "openrouter", + "family": "~anthropic", + "created_at": "2026-04-21 18:16:01 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 25.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the Claude Opus family.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "tool_choice", + "tools", + "verbosity" + ] + } + }, + { + "id": "~anthropic/claude-sonnet-latest", + "name": "Anthropic Claude Sonnet Latest", + "provider": "openrouter", + "family": "~anthropic", + "created_at": "2026-04-27 19:32:48 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3.0, + "output_per_million": 15.0, + "cache_read_input_per_million": 0.3 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the Anthropic Claude Sonnet family.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 1000000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_p", + "verbosity" + ] + } + }, + { + "id": "~google/gemini-flash-latest", + "name": "Google Gemini Flash Latest", + "provider": "openrouter", + "family": "~google", + "created_at": "2026-04-27 19:33:18 UTC", + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.5, + "output_per_million": 3.0, + "cache_read_input_per_million": 0.049999999999999996, + "reasoning_output_per_million": 3.0 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the Google Gemini Flash family.", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "text", + "image", + "file", + "audio", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "~google/gemini-pro-latest", + "name": "Google Gemini Pro Latest", + "provider": "openrouter", + "family": "~google", + "created_at": "2026-04-27 19:34:11 UTC", + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "audio", + "file", + "image", + "text", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 2.0, + "output_per_million": 12.0, + "cache_read_input_per_million": 0.19999999999999998, + "reasoning_output_per_million": 12.0 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the Google Gemini Pro family.", + "architecture": { + "modality": "text+image+file+audio+video->text", + "input_modalities": [ + "audio", + "file", + "image", + "text", + "video" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 1048576, + "max_completion_tokens": 65536, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_tokens", + "reasoning", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_p" + ] + } + }, + { + "id": "~moonshotai/kimi-latest", + "name": "MoonshotAI Kimi Latest", + "provider": "openrouter", + "family": "~moonshotai", + "created_at": "2026-04-27 19:33:48 UTC", + "context_window": 262144, + "max_output_tokens": 16384, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "predicted_outputs" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.75, + "output_per_million": 3.5, + "cache_read_input_per_million": 0.15 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the MoonshotAI Kimi family.", + "architecture": { + "modality": "text+image->text", + "input_modalities": [ + "text", + "image" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 262144, + "max_completion_tokens": 16384, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "frequency_penalty", + "include_reasoning", + "logit_bias", + "logprobs", + "max_tokens", + "min_p", + "parallel_tool_calls", + "presence_penalty", + "reasoning", + "reasoning_effort", + "repetition_penalty", + "response_format", + "seed", + "stop", + "structured_outputs", + "temperature", + "tool_choice", + "tools", + "top_k", + "top_logprobs", + "top_p" + ] + } + }, + { + "id": "~openai/gpt-latest", + "name": "OpenAI GPT Latest", + "provider": "openrouter", + "family": "~openai", + "created_at": "2026-04-27 19:32:14 UTC", + "context_window": 1050000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "file", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5.0, + "output_per_million": 30.0, + "cache_read_input_per_million": 0.5 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the OpenAI GPT family.", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 1050000, + "max_completion_tokens": 128000, + "is_moderated": true + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, + { + "id": "~openai/gpt-mini-latest", + "name": "OpenAI GPT Mini Latest", + "provider": "openrouter", + "family": "~openai", + "created_at": "2026-04-27 19:34:31 UTC", + "context_window": 400000, + "max_output_tokens": 128000, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "file", + "image", + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.75, + "output_per_million": 4.5, + "cache_read_input_per_million": 0.075 + } + } + }, + "metadata": { + "description": "This model always redirects to the latest model in the OpenAI GPT Mini family.", + "architecture": { + "modality": "text+image+file->text", + "input_modalities": [ + "file", + "image", + "text" + ], + "output_modalities": [ + "text" + ], + "tokenizer": "Router", + "instruct_type": null + }, + "top_provider": { + "context_length": 400000, + "max_completion_tokens": 128000, + "is_moderated": false + }, + "per_request_limits": null, + "supported_parameters": [ + "include_reasoning", + "max_completion_tokens", + "max_tokens", + "reasoning", + "response_format", + "seed", + "structured_outputs", + "tool_choice", + "tools" + ] + } + }, { "id": "sonar", "name": "Sonar", "provider": "perplexity", "family": "sonar", - "created_at": "2024-01-01 00:00:00 +0530", + "created_at": "2024-01-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": "2025-09-01", @@ -22563,7 +58242,9 @@ "text" ] }, - "capabilities": [], + "capabilities": [ + "vision" + ], "pricing": { "text_tokens": { "standard": { @@ -22595,7 +58276,7 @@ "name": "Perplexity Sonar Deep Research", "provider": "perplexity", "family": null, - "created_at": "2025-02-01 00:00:00 +0530", + "created_at": "2025-02-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 32768, "knowledge_cutoff": null, @@ -22643,7 +58324,7 @@ "name": "Sonar Pro", "provider": "perplexity", "family": "sonar-pro", - "created_at": "2024-01-01 00:00:00 +0530", + "created_at": "2024-01-01 00:00:00 UTC", "context_window": 200000, "max_output_tokens": 8192, "knowledge_cutoff": "2025-09-01", @@ -22685,12 +58366,39 @@ "knowledge": "2025-09-01" } }, + { + "id": "sonar-reasoning", + "name": "sonar-reasoning", + "provider": "perplexity", + "family": null, + "created_at": null, + "context_window": 128000, + "max_output_tokens": 4096, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "vision", + "reasoning" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.0, + "output_per_million": 5.0 + } + } + }, + "metadata": {} + }, { "id": "sonar-reasoning-pro", "name": "Sonar Reasoning Pro", "provider": "perplexity", "family": "sonar-reasoning", - "created_at": "2024-01-01 00:00:00 +0530", + "created_at": "2024-01-01 00:00:00 UTC", "context_window": 128000, "max_output_tokens": 4096, "knowledge_cutoff": "2025-09-01", @@ -22734,17 +58442,18 @@ } }, { - "id": "deepseek-ai/deepseek-v3.1-maas", - "name": "DeepSeek V3.1", + "id": "claude-3-5-haiku@20241022", + "name": "Claude Haiku 3.5", "provider": "vertexai", - "family": "deepseek", - "created_at": "2025-08-28 00:00:00 +0530", - "context_window": 163840, - "max_output_tokens": 32768, - "knowledge_cutoff": null, + "family": "claude-haiku", + "created_at": "2024-10-22 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 8192, + "knowledge_cutoff": "2024-07-31", "modalities": { "input": [ "text", + "image", "pdf" ], "output": [ @@ -22753,47 +58462,51 @@ }, "capabilities": [ "function_calling", - "structured_output", - "reasoning", "vision" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.6, - "output_per_million": 1.7 + "input_per_million": 0.8, + "output_per_million": 4, + "cache_read_input_per_million": 0.08, + "cache_write_input_per_million": 1 } } }, "metadata": { "source": "models.dev", "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, + "open_weights": false, + "attachment": true, "temperature": true, - "last_updated": "2025-08-28", + "last_updated": "2024-10-22", "cost": { - "input": 0.6, - "output": 1.7 + "input": 0.8, + "output": 4, + "cache_read": 0.08, + "cache_write": 1 }, "limit": { - "context": 163840, - "output": 32768 - } + "context": 200000, + "output": 8192 + }, + "knowledge": "2024-07-31" } }, { - "id": "deepseek-ai/deepseek-v3.2-maas", - "name": "DeepSeek V3.2", + "id": "claude-3-5-sonnet@20241022", + "name": "Claude Sonnet 3.5 v2", "provider": "vertexai", - "family": "deepseek", - "created_at": "2025-12-17 00:00:00 +0530", - "context_window": 163840, - "max_output_tokens": 65536, - "knowledge_cutoff": null, + "family": "claude-sonnet", + "created_at": "2024-10-22 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 8192, + "knowledge_cutoff": "2024-04-30", "modalities": { "input": [ "text", + "image", "pdf" ], "output": [ @@ -22802,35 +58515,862 @@ }, "capabilities": [ "function_calling", - "structured_output", - "reasoning", "vision" ], "pricing": { "text_tokens": { "standard": { - "input_per_million": 0.56, - "output_per_million": 1.68, - "cached_input_per_million": 0.056 + "input_per_million": 3, + "output_per_million": 15, + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 } } }, "metadata": { "source": "models.dev", "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, + "open_weights": false, + "attachment": true, "temperature": true, - "last_updated": "2026-04-04", + "last_updated": "2024-10-22", "cost": { - "input": 0.56, - "output": 1.68, - "cache_read": 0.056 + "input": 3, + "output": 15, + "cache_read": 0.3, + "cache_write": 3.75 }, "limit": { - "context": 163840, - "output": 65536 + "context": 200000, + "output": 8192 + }, + "knowledge": "2024-04-30" + } + }, + { + "id": "claude-3-7-sonnet@20250219", + "name": "Claude Sonnet 3.7", + "provider": "vertexai", + "family": "claude-sonnet", + "created_at": "2025-02-19 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": "2024-10-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3, + "output_per_million": 15, + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 + } } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-02-19", + "cost": { + "input": 3, + "output": 15, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + }, + "knowledge": "2024-10-31" + } + }, + { + "id": "claude-haiku-4-5@20251001", + "name": "Claude Haiku 4.5", + "provider": "vertexai", + "family": "claude-haiku", + "created_at": "2025-10-15 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": "2025-02-28", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1, + "output_per_million": 5, + "cache_read_input_per_million": 0.1, + "cache_write_input_per_million": 1.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-10-15", + "cost": { + "input": 1, + "output": 5, + "cache_read": 0.1, + "cache_write": 1.25 + }, + "limit": { + "context": 200000, + "output": 64000 + }, + "knowledge": "2025-02-28" + } + }, + { + "id": "claude-opus-4-1@20250805", + "name": "Claude Opus 4.1", + "provider": "vertexai", + "family": "claude-opus", + "created_at": "2025-08-05 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 32000, + "knowledge_cutoff": "2025-03-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 15, + "output_per_million": 75, + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-08-05", + "cost": { + "input": 15, + "output": 75, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + }, + "knowledge": "2025-03-31" + } + }, + { + "id": "claude-opus-4-5@20251101", + "name": "Claude Opus 4.5", + "provider": "vertexai", + "family": "claude-opus", + "created_at": "2025-11-01 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": "2025-03-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-11-01", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25 + }, + "limit": { + "context": 200000, + "output": 64000 + }, + "knowledge": "2025-03-31" + } + }, + { + "id": "claude-opus-4-6@default", + "name": "Claude Opus 4.6", + "provider": "vertexai", + "family": "claude-opus", + "created_at": "2026-02-05 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2025-05-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-03-13", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25, + "context_over_200k": { + "input": 10, + "output": 37.5, + "cache_read": 1, + "cache_write": 12.5 + } + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2025-05-31" + } + }, + { + "id": "claude-opus-4-7@default", + "name": "Claude Opus 4.7", + "provider": "vertexai", + "family": "claude-opus", + "created_at": "2026-04-16 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 128000, + "knowledge_cutoff": "2026-01-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 5, + "output_per_million": 25, + "cache_read_input_per_million": 0.5, + "cache_write_input_per_million": 6.25 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": false, + "last_updated": "2026-04-16", + "cost": { + "input": 5, + "output": 25, + "cache_read": 0.5, + "cache_write": 6.25, + "context_over_200k": { + "input": 10, + "output": 37.5, + "cache_read": 1, + "cache_write": 12.5 + } + }, + "limit": { + "context": 1000000, + "output": 128000 + }, + "knowledge": "2026-01-31" + } + }, + { + "id": "claude-opus-4@20250514", + "name": "Claude Opus 4", + "provider": "vertexai", + "family": "claude-opus", + "created_at": "2025-05-22 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 32000, + "knowledge_cutoff": "2025-03-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 15, + "output_per_million": 75, + "cache_read_input_per_million": 1.5, + "cache_write_input_per_million": 18.75 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-05-22", + "cost": { + "input": 15, + "output": 75, + "cache_read": 1.5, + "cache_write": 18.75 + }, + "limit": { + "context": 200000, + "output": 32000 + }, + "knowledge": "2025-03-31" + } + }, + { + "id": "claude-sonnet-4-5@20250929", + "name": "Claude Sonnet 4.5", + "provider": "vertexai", + "family": "claude-sonnet", + "created_at": "2025-09-29 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": "2025-07-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3, + "output_per_million": 15, + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-09-29", + "cost": { + "input": 3, + "output": 15, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + }, + "knowledge": "2025-07-31" + } + }, + { + "id": "claude-sonnet-4-6@default", + "name": "Claude Sonnet 4.6", + "provider": "vertexai", + "family": "claude-sonnet", + "created_at": "2026-02-17 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": "2025-08-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3, + "output_per_million": 15, + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-03-13", + "cost": { + "input": 3, + "output": 15, + "cache_read": 0.3, + "cache_write": 3.75, + "context_over_200k": { + "input": 6, + "output": 22.5, + "cache_read": 0.6, + "cache_write": 7.5 + } + }, + "limit": { + "context": 200000, + "output": 64000 + }, + "knowledge": "2025-08-31" + } + }, + { + "id": "claude-sonnet-4@20250514", + "name": "Claude Sonnet 4", + "provider": "vertexai", + "family": "claude-sonnet", + "created_at": "2025-05-22 00:00:00 UTC", + "context_window": 200000, + "max_output_tokens": 64000, + "knowledge_cutoff": "2025-03-31", + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "reasoning", + "vision" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 3, + "output_per_million": 15, + "cache_read_input_per_million": 0.3, + "cache_write_input_per_million": 3.75 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2025-05-22", + "cost": { + "input": 3, + "output": 15, + "cache_read": 0.3, + "cache_write": 3.75 + }, + "limit": { + "context": 200000, + "output": 64000 + }, + "knowledge": "2025-03-31" + } + }, + { + "id": "gemini-1.5-flash", + "name": "Gemini 1.5 Flash", + "provider": "vertexai", + "family": "gemini-flash", + "created_at": "2024-05-14 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.075, + "output_per_million": 0.3, + "cache_read_input_per_million": 0.01875 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-05-14", + "cost": { + "input": 0.075, + "output": 0.3, + "cache_read": 0.01875 + }, + "limit": { + "context": 1000000, + "output": 8192 + }, + "knowledge": "2024-04" + } + }, + { + "id": "gemini-1.5-flash-002", + "name": "gemini-1.5-flash-002", + "provider": "vertexai", + "family": "gemini-1.5", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "gemini-1.5-flash-8b", + "name": "Gemini 1.5 Flash-8B", + "provider": "vertexai", + "family": "gemini-flash", + "created_at": "2024-10-03 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.0375, + "output_per_million": 0.15, + "cache_read_input_per_million": 0.01 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-10-03", + "cost": { + "input": 0.0375, + "output": 0.15, + "cache_read": 0.01 + }, + "limit": { + "context": 1000000, + "output": 8192 + }, + "knowledge": "2024-04" + } + }, + { + "id": "gemini-1.5-pro", + "name": "Gemini 1.5 Pro", + "provider": "vertexai", + "family": "gemini-pro", + "created_at": "2024-02-15 00:00:00 UTC", + "context_window": 1000000, + "max_output_tokens": 8192, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "audio", + "video" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 1.25, + "output_per_million": 5, + "cache_read_input_per_million": 0.3125 + } + } + }, + "metadata": { + "source": "models.dev", + "provider_id": "google", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2024-02-15", + "cost": { + "input": 1.25, + "output": 5, + "cache_read": 0.3125 + }, + "limit": { + "context": 1000000, + "output": 8192 + }, + "knowledge": "2024-04" + } + }, + { + "id": "gemini-1.5-pro-002", + "name": "gemini-1.5-pro-002", + "provider": "vertexai", + "family": "gemini-1.5", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": "PROPRIETARY", + "launch_stage": "GA", + "supported_actions": { + "openNotebook": { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/use-cases/retail/product_attributes_extraction.ipynb" + } + }, + "title": "Open Notebook", + "resourceTitle": "Notebook", + "resourceUseCase": "Product Attributes Extraction", + "resourceDescription": "Extract product descriptions and attribute json from images using Gemini 1.5 Pro. This notebook also shows the use of self-correcting prompt to improve the quality of the output." + }, + "openGenerationAiStudio": { + "references": { + "us-central1": { + "uri": "https://console.cloud.google.com/vertex-ai/studio/freeform?model=gemini-1.5-pro-002" + } + } + }, + "openEvaluationPipeline": { + "references": { + "us-central1": { + "uri": "https://console.cloud.google.com/vertex-ai/pipelines/vertex-ai-templates/autosxs-template" + } + }, + "title": "Evaluate" + }, + "openNotebooks": { + "notebooks": [ + { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_1_5_pro.ipynb" + } + }, + "title": "Open Notebook" + }, + { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_1_5_pro.ipynb" + } + }, + "title": "Open Notebook", + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex AI Gemini API 1.5 Pro", + "resourceDescription": "Use the Vertex AI Gemini API 1.5 Pro model to process images, video, audio, and text simultaneously." + }, + { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/use-cases/retail/product_attributes_extraction.ipynb" + } + }, + "title": "Open Notebook", + "resourceTitle": "Notebook", + "resourceUseCase": "Product Attributes Extraction", + "resourceDescription": "Extract product descriptions and attribute json from images using Gemini 1.5 Pro. This notebook also shows the use of self-correcting prompt to improve the quality of the output." + } + ] + } + }, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-1.5-pro-002@default" } }, { @@ -22838,7 +59378,7 @@ "name": "Gemini 2.0 Flash", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2024-12-11 00:00:00 +0530", + "created_at": "2024-12-11 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -22856,18 +59396,56 @@ }, "capabilities": [ "function_calling", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": { + "openNotebook": { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_2_0_flash.ipynb" + } + }, + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex Serving", + "resourceDescription": "Intro to Gemini 2.0 Flash." + }, + "openGenerationAiStudio": { + "references": { + "us-central1": { + "uri": "https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-2.0-flash-001" + } + } + }, + "openNotebooks": { + "notebooks": [ + { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_2_0_flash.ipynb" + } + }, + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex Serving", + "resourceDescription": "Intro to Gemini 2.0 Flash." + } + ] + } + }, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.0-flash@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -22886,12 +59464,92 @@ "knowledge": "2024-06" } }, + { + "id": "gemini-2.0-flash-001", + "name": "gemini-2.0-flash-001", + "provider": "vertexai", + "family": "gemini-2", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": { + "openNotebook": { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_2_0_flash.ipynb" + } + }, + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex Serving", + "resourceDescription": "Intro to Gemini 2.0 Flash." + }, + "openGenerationAiStudio": { + "references": { + "us-central1": { + "uri": "https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-2.0-flash-001" + } + } + }, + "openNotebooks": { + "notebooks": [ + { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_2_0_flash.ipynb" + } + }, + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex Serving", + "resourceDescription": "Intro to Gemini 2.0 Flash." + } + ] + } + }, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.0-flash-001@default" + } + }, + { + "id": "gemini-2.0-flash-exp", + "name": "gemini-2.0-flash-exp", + "provider": "vertexai", + "family": "gemini-2", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, { "id": "gemini-2.0-flash-lite", "name": "Gemini 2.0 Flash Lite", "provider": "vertexai", "family": "gemini-flash-lite", - "created_at": "2024-12-11 00:00:00 +0530", + "created_at": "2024-12-11 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 8192, "knowledge_cutoff": null, @@ -22937,12 +59595,38 @@ "knowledge": "2024-06" } }, + { + "id": "gemini-2.0-flash-lite-001", + "name": "gemini-2.0-flash-lite-001", + "provider": "vertexai", + "family": "gemini-2", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.0-flash-lite-001@default" + } + }, { "id": "gemini-2.5-flash", "name": "Gemini 2.5 Flash", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -22961,18 +59645,25 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075, + "cache_write_input_per_million": 0.383 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-flash@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -22997,7 +59688,7 @@ "name": "Gemini 2.5 Flash Lite", "provider": "vertexai", "family": "gemini-flash-lite", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23016,18 +59707,24 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-flash-lite@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -23051,7 +59748,7 @@ "name": "Gemini 2.5 Flash Lite Preview 06-17", "provider": "vertexai", "family": "gemini-flash-lite", - "created_at": "2025-06-17 00:00:00 +0530", + "created_at": "2025-06-17 00:00:00 UTC", "context_window": 65536, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23077,7 +59774,7 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -23105,7 +59802,7 @@ "name": "Gemini 2.5 Flash Lite Preview 09-25", "provider": "vertexai", "family": "gemini-flash-lite", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23131,7 +59828,7 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -23159,7 +59856,7 @@ "name": "Gemini 2.5 Flash Preview 04-17", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2025-04-17 00:00:00 +0530", + "created_at": "2025-04-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23178,18 +59875,32 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.0375 + "cache_read_input_per_million": 0.0375 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "PUBLIC_PREVIEW", + "supported_actions": { + "openGenerationAiStudio": { + "references": { + "us-central1": { + "uri": "https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-2.5-flash-preview-04-17" + } + } + } + }, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-flash-preview-04-17@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -23213,7 +59924,7 @@ "name": "Gemini 2.5 Flash Preview 05-20", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23239,7 +59950,7 @@ "standard": { "input_per_million": 0.15, "output_per_million": 0.6, - "cached_input_per_million": 0.0375 + "cache_read_input_per_million": 0.0375 } } }, @@ -23267,7 +59978,7 @@ "name": "Gemini 2.5 Flash Preview 09-25", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23293,7 +60004,8 @@ "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075, + "cache_write_input_per_million": 0.383 } } }, @@ -23317,12 +60029,38 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-2.5-flash-tts", + "name": "gemini-2.5-flash-tts", + "provider": "vertexai", + "family": "gemini-2", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-flash-tts@default" + } + }, { "id": "gemini-2.5-pro", "name": "Gemini 2.5 Pro", "provider": "vertexai", "family": "gemini-pro", - "created_at": "2025-03-20 00:00:00 +0530", + "created_at": "2025-03-20 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23341,18 +60079,24 @@ "capabilities": [ "function_calling", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.125 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-pro@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -23362,7 +60106,12 @@ "cost": { "input": 1.25, "output": 10, - "cache_read": 0.31 + "cache_read": 0.125, + "context_over_200k": { + "input": 2.5, + "output": 15, + "cache_read": 0.25 + } }, "limit": { "context": 1048576, @@ -23371,12 +60120,70 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-2.5-pro-exp-03-25", + "name": "gemini-2.5-pro-exp-03-25", + "provider": "vertexai", + "family": "gemini-2", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "EXPERIMENTAL", + "supported_actions": { + "openNotebook": { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_2_5_pro.ipynb" + } + }, + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex Serving", + "resourceDescription": "Intro to Gemini 2.5 Pro." + }, + "openGenerationAiStudio": { + "references": { + "us-central1": { + "uri": "https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-2.5-pro-exp-03-25" + } + } + }, + "openNotebooks": { + "notebooks": [ + { + "references": { + "us-central1": { + "uri": "https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/gemini/getting-started/intro_gemini_2_5_pro.ipynb" + } + }, + "resourceTitle": "Notebook", + "resourceUseCase": "Vertex Serving", + "resourceDescription": "Intro to Gemini 2.5 Pro." + } + ] + } + }, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-pro-exp-03-25@default" + } + }, { "id": "gemini-2.5-pro-preview-05-06", "name": "Gemini 2.5 Pro Preview 05-06", "provider": "vertexai", "family": "gemini-pro", - "created_at": "2025-05-06 00:00:00 +0530", + "created_at": "2025-05-06 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23402,7 +60209,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.31 } } }, @@ -23430,7 +60237,7 @@ "name": "Gemini 2.5 Pro Preview 06-05", "provider": "vertexai", "family": "gemini-pro", - "created_at": "2025-06-05 00:00:00 +0530", + "created_at": "2025-06-05 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23456,7 +60263,7 @@ "standard": { "input_per_million": 1.25, "output_per_million": 10, - "cached_input_per_million": 0.31 + "cache_read_input_per_million": 0.31 } } }, @@ -23479,12 +60286,38 @@ "knowledge": "2025-01" } }, + { + "id": "gemini-2.5-pro-tts", + "name": "gemini-2.5-pro-tts", + "provider": "vertexai", + "family": "gemini-2", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-2.5-pro-tts@default" + } + }, { "id": "gemini-3-flash-preview", "name": "Gemini 3 Flash Preview", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2025-12-17 00:00:00 +0530", + "created_at": "2025-12-17 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23504,18 +60337,24 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 0.5, "output_per_million": 3, - "cached_input_per_million": 0.05 + "cache_read_input_per_million": 0.05 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "PUBLIC_PREVIEW", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-3-flash-preview@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -23544,7 +60383,7 @@ "name": "Gemini 3 Pro Preview", "provider": "vertexai", "family": "gemini-pro", - "created_at": "2025-11-18 00:00:00 +0530", + "created_at": "2025-11-18 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23571,7 +60410,7 @@ "standard": { "input_per_million": 2, "output_per_million": 12, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, @@ -23600,11 +60439,68 @@ } }, { - "id": "gemini-3.1-pro-preview", - "name": "Gemini 3.1 Pro Preview", + "id": "gemini-3.1-flash-image-preview", + "name": "Gemini 3.1 Flash Image (Preview)", "provider": "vertexai", - "family": "gemini-pro", - "created_at": "2026-02-19 00:00:00 +0530", + "family": "gemini-flash", + "created_at": "2026-02-26 00:00:00 UTC", + "context_window": 131072, + "max_output_tokens": 32768, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "pdf" + ], + "output": [ + "text", + "image" + ] + }, + "capabilities": [ + "reasoning", + "vision", + "streaming", + "function_calling" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 60 + } + } + }, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "PUBLIC_PREVIEW", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-3.1-flash-image-preview@default", + "source": "models.dev", + "provider_id": "google", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-02-26", + "cost": { + "input": 0.25, + "output": 60 + }, + "limit": { + "context": 131072, + "output": 32768 + }, + "knowledge": "2025-01" + } + }, + { + "id": "gemini-3.1-flash-lite-preview", + "name": "Gemini 3.1 Flash Lite Preview", + "provider": "vertexai", + "family": "gemini-flash-lite", + "created_at": "2026-03-03 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23624,18 +60520,87 @@ "function_calling", "structured_output", "reasoning", - "vision" + "vision", + "streaming" + ], + "pricing": { + "text_tokens": { + "standard": { + "input_per_million": 0.25, + "output_per_million": 1.5, + "cache_read_input_per_million": 0.025, + "cache_write_input_per_million": 1 + } + } + }, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "PUBLIC_PREVIEW", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-3.1-flash-lite-preview@default", + "source": "models.dev", + "provider_id": "google-vertex", + "open_weights": false, + "attachment": true, + "temperature": true, + "last_updated": "2026-03-03", + "cost": { + "input": 0.25, + "output": 1.5, + "cache_read": 0.025, + "cache_write": 1 + }, + "limit": { + "context": 1048576, + "output": 65536 + }, + "knowledge": "2025-01" + } + }, + { + "id": "gemini-3.1-pro-preview", + "name": "Gemini 3.1 Pro Preview", + "provider": "vertexai", + "family": "gemini-pro", + "created_at": "2026-02-19 00:00:00 UTC", + "context_window": 1048576, + "max_output_tokens": 65536, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image", + "video", + "audio", + "pdf" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "function_calling", + "structured_output", + "reasoning", + "vision", + "streaming" ], "pricing": { "text_tokens": { "standard": { "input_per_million": 2, "output_per_million": 12, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "PUBLIC_PREVIEW", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-3.1-pro-preview@default", "source": "models.dev", "provider_id": "google-vertex", "open_weights": false, @@ -23664,7 +60629,7 @@ "name": "Gemini 3.1 Pro Preview Custom Tools", "provider": "vertexai", "family": "gemini-pro", - "created_at": "2026-02-19 00:00:00 +0530", + "created_at": "2026-02-19 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23691,7 +60656,7 @@ "standard": { "input_per_million": 2, "output_per_million": 12, - "cached_input_per_million": 0.2 + "cache_read_input_per_million": 0.2 } } }, @@ -23724,7 +60689,7 @@ "name": "Gemini Embedding 001", "provider": "vertexai", "family": "gemini", - "created_at": "2025-05-20 00:00:00 +0530", + "created_at": "2025-05-20 00:00:00 UTC", "context_window": 2048, "max_output_tokens": 3072, "knowledge_cutoff": null, @@ -23733,10 +60698,13 @@ "text" ], "output": [ - "text" + "embeddings" ] }, - "capabilities": [], + "capabilities": [ + "streaming", + "function_calling" + ], "pricing": { "text_tokens": { "standard": { @@ -23762,12 +60730,82 @@ "knowledge": "2025-05" } }, + { + "id": "gemini-embedding-2", + "name": "gemini-embedding-2", + "provider": "vertexai", + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-embedding-2@default" + } + }, + { + "id": "gemini-exp-1121", + "name": "gemini-exp-1121", + "provider": "vertexai", + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "gemini-exp-1206", + "name": "gemini-exp-1206", + "provider": "vertexai", + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, { "id": "gemini-flash-latest", "name": "Gemini Flash Latest", "provider": "vertexai", "family": "gemini-flash", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23793,7 +60831,8 @@ "standard": { "input_per_million": 0.3, "output_per_million": 2.5, - "cached_input_per_million": 0.075 + "cache_read_input_per_million": 0.075, + "cache_write_input_per_million": 0.383 } } }, @@ -23822,7 +60861,7 @@ "name": "Gemini Flash-Lite Latest", "provider": "vertexai", "family": "gemini-flash-lite", - "created_at": "2025-09-25 00:00:00 +0530", + "created_at": "2025-09-25 00:00:00 UTC", "context_window": 1048576, "max_output_tokens": 65536, "knowledge_cutoff": null, @@ -23848,7 +60887,7 @@ "standard": { "input_per_million": 0.1, "output_per_million": 0.4, - "cached_input_per_million": 0.025 + "cache_read_input_per_million": 0.025 } } }, @@ -23872,13 +60911,149 @@ } }, { - "id": "meta/llama-3.3-70b-instruct-maas", - "name": "Llama 3.3 70B Instruct", + "id": "gemini-live-2.5-flash-native-audio", + "name": "gemini-live-2.5-flash-native-audio", "provider": "vertexai", - "family": "llama", - "created_at": "2025-04-29 00:00:00 +0530", - "context_window": 128000, - "max_output_tokens": 8192, + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "version_id": "default", + "open_source_category": null, + "launch_stage": "GA", + "supported_actions": null, + "publisher_model_template": "projects/{project}/locations/{location}/publishers/google/models/gemini-live-2.5-flash-native-audio@default" + } + }, + { + "id": "gemini-pro", + "name": "gemini-pro", + "provider": "vertexai", + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "gemini-pro-vision", + "name": "gemini-pro-vision", + "provider": "vertexai", + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "text-embedding-004", + "name": "text-embedding-004", + "provider": "vertexai", + "family": "text-embedding", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "text-embedding-005", + "name": "text-embedding-005", + "provider": "vertexai", + "family": "text-embedding", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "text-multilingual-embedding-002", + "name": "text-multilingual-embedding-002", + "provider": "vertexai", + "family": "gemini", + "created_at": null, + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [], + "output": [] + }, + "capabilities": [ + "streaming", + "function_calling" + ], + "pricing": {}, + "metadata": { + "source": "known_models" + } + }, + { + "id": "grok-3", + "name": "Grok 3", + "provider": "xai", + "family": "grok", + "created_at": "2025-04-04 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { "input": [ @@ -23889,43 +61064,53 @@ ] }, "capabilities": [ + "streaming", "function_calling", "structured_output" ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.72, - "output_per_million": 0.72 - } - } - }, + "pricing": {}, "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2025-04-29", - "cost": { - "input": 0.72, - "output": 0.72 - }, - "limit": { - "context": 128000, - "output": 8192 - }, - "knowledge": "2023-12" + "object": "model", + "owned_by": "xai" } }, { - "id": "meta/llama-4-maverick-17b-128e-instruct-maas", - "name": "Llama 4 Maverick 17B 128E Instruct", - "provider": "vertexai", - "family": "llama", - "created_at": "2025-04-29 00:00:00 +0530", - "context_window": 524288, - "max_output_tokens": 8192, + "id": "grok-3-mini", + "name": "Grok 3 Mini", + "provider": "xai", + "family": "grok", + "created_at": "2025-04-04 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "reasoning" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4-0709", + "name": "Grok 4 0709", + "provider": "xai", + "family": "grok", + "created_at": "2025-07-09 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { "input": [ @@ -23937,287 +61122,148 @@ ] }, "capabilities": [ - "function_calling", - "structured_output", - "vision" - ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.35, - "output_per_million": 1.15 - } - } - }, - "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": true, - "temperature": true, - "last_updated": "2025-04-29", - "cost": { - "input": 0.35, - "output": 1.15 - }, - "limit": { - "context": 524288, - "output": 8192 - }, - "knowledge": "2024-08" - } - }, - { - "id": "moonshotai/kimi-k2-thinking-maas", - "name": "Kimi K2 Thinking", - "provider": "vertexai", - "family": "kimi-thinking", - "created_at": "2025-11-13 00:00:00 +0530", - "context_window": 262144, - "max_output_tokens": 262144, - "knowledge_cutoff": null, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "capabilities": [ - "function_calling", - "structured_output", - "reasoning" - ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.6, - "output_per_million": 2.5 - } - } - }, - "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2025-11-13", - "interleaved": { - "field": "reasoning_content" - }, - "cost": { - "input": 0.6, - "output": 2.5 - }, - "limit": { - "context": 262144, - "output": 262144 - }, - "knowledge": "2024-08" - } - }, - { - "id": "openai/gpt-oss-120b-maas", - "name": "GPT OSS 120B", - "provider": "vertexai", - "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", - "context_window": 131072, - "max_output_tokens": 32768, - "knowledge_cutoff": null, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "capabilities": [ - "function_calling", - "reasoning" - ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.09, - "output_per_million": 0.36 - } - } - }, - "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2025-08-05", - "cost": { - "input": 0.09, - "output": 0.36 - }, - "limit": { - "context": 131072, - "output": 32768 - } - } - }, - { - "id": "openai/gpt-oss-20b-maas", - "name": "GPT OSS 20B", - "provider": "vertexai", - "family": "gpt-oss", - "created_at": "2025-08-05 00:00:00 +0530", - "context_window": 131072, - "max_output_tokens": 32768, - "knowledge_cutoff": null, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "capabilities": [ - "function_calling", - "reasoning" - ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.07, - "output_per_million": 0.25 - } - } - }, - "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2025-08-05", - "cost": { - "input": 0.07, - "output": 0.25 - }, - "limit": { - "context": 131072, - "output": 32768 - } - } - }, - { - "id": "qwen/qwen3-235b-a22b-instruct-2507-maas", - "name": "Qwen3 235B A22B Instruct", - "provider": "vertexai", - "family": "qwen", - "created_at": "2025-08-13 00:00:00 +0530", - "context_window": 262144, - "max_output_tokens": 16384, - "knowledge_cutoff": null, - "modalities": { - "input": [ - "text" - ], - "output": [ - "text" - ] - }, - "capabilities": [ - "function_calling", - "structured_output", - "reasoning" - ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.22, - "output_per_million": 0.88 - } - } - }, - "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2025-08-13", - "cost": { - "input": 0.22, - "output": 0.88 - }, - "limit": { - "context": 262144, - "output": 16384 - } - } - }, - { - "id": "zai-org/glm-4.7-maas", - "name": "GLM-4.7", - "provider": "vertexai", - "family": "glm", - "created_at": "2026-01-06 00:00:00 +0530", - "context_window": 200000, - "max_output_tokens": 128000, - "knowledge_cutoff": null, - "modalities": { - "input": [ - "text", - "pdf" - ], - "output": [ - "text" - ] - }, - "capabilities": [ + "streaming", "function_calling", "structured_output", "reasoning", "vision" ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 0.6, - "output_per_million": 2.2 - } - } - }, + "pricing": {}, "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2026-01-06", - "interleaved": { - "field": "reasoning_content" - }, - "cost": { - "input": 0.6, - "output": 2.2 - }, - "limit": { - "context": 200000, - "output": 128000 - }, - "knowledge": "2025-04" + "object": "model", + "owned_by": "xai" } }, { - "id": "zai-org/glm-5-maas", - "name": "GLM-5", - "provider": "vertexai", - "family": "glm", - "created_at": "2026-02-11 00:00:00 +0530", - "context_window": 202752, - "max_output_tokens": 131072, + "id": "grok-4-1-fast-non-reasoning", + "name": "Grok 4 1 Fast Non Reasoning", + "provider": "xai", + "family": "grok", + "created_at": "2025-11-19 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4-1-fast-reasoning", + "name": "Grok 4 1 Fast Reasoning", + "provider": "xai", + "family": "grok", + "created_at": "2025-11-19 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4-fast-non-reasoning", + "name": "Grok 4 Fast Non Reasoning", + "provider": "xai", + "family": "grok", + "created_at": "2025-09-04 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4-fast-reasoning", + "name": "Grok 4 Fast Reasoning", + "provider": "xai", + "family": "grok", + "created_at": "2025-09-04 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text", + "image" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", + "reasoning", + "vision" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4.20-0309-non-reasoning", + "name": "Grok 4.20 0309 Non Reasoning", + "provider": "xai", + "family": "grok", + "created_at": "2026-03-09 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, "knowledge_cutoff": null, "modalities": { "input": [ @@ -24228,37 +61274,239 @@ ] }, "capabilities": [ + "streaming", "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4.20-0309-reasoning", + "name": "Grok 4.20 0309 Reasoning", + "provider": "xai", + "family": "grok", + "created_at": "2026-03-09 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4.20-multi-agent-0309", + "name": "Grok 4.20 Multi Agent 0309", + "provider": "xai", + "family": "grok", + "created_at": "2026-03-09 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-4.3", + "name": "Grok 4.3", + "provider": "xai", + "family": "grok", + "created_at": "2026-04-17 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-code-fast-1", + "name": "Grok Code Fast 1", + "provider": "xai", + "family": "grok", + "created_at": "2025-08-24 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output", "reasoning" ], - "pricing": { - "text_tokens": { - "standard": { - "input_per_million": 1, - "output_per_million": 3.2, - "cached_input_per_million": 0.1 - } - } - }, + "pricing": {}, "metadata": { - "source": "models.dev", - "provider_id": "google-vertex", - "open_weights": true, - "attachment": false, - "temperature": true, - "last_updated": "2026-02-11", - "interleaved": { - "field": "reasoning_content" - }, - "cost": { - "input": 1, - "output": 3.2, - "cache_read": 0.1 - }, - "limit": { - "context": 202752, - "output": 131072 - } + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-imagine-image", + "name": "Grok Imagine Image", + "provider": "xai", + "family": "grok", + "created_at": "2026-01-28 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-imagine-image-pro", + "name": "Grok Imagine Image Pro", + "provider": "xai", + "family": "grok", + "created_at": "2026-01-28 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-imagine-image-quality", + "name": "Grok Imagine Image Quality", + "provider": "xai", + "family": "grok", + "created_at": "2026-04-03 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" + } + }, + { + "id": "grok-imagine-video", + "name": "Grok Imagine Video", + "provider": "xai", + "family": "grok", + "created_at": "2026-01-28 00:00:00 UTC", + "context_window": null, + "max_output_tokens": null, + "knowledge_cutoff": null, + "modalities": { + "input": [ + "text" + ], + "output": [ + "text" + ] + }, + "capabilities": [ + "streaming", + "function_calling", + "structured_output" + ], + "pricing": {}, + "metadata": { + "object": "model", + "owned_by": "xai" } } ] \ No newline at end of file