From cc5974da9bec82fccf7fcba1ed14b7326dc486c8 Mon Sep 17 00:00:00 2001
From: Muhsin Keloth
{{ description }}
- {{ title }}
-
+
+ {{ title }}
+
+
+
+ {{ t('CONVERSATION_SIDEBAR.SHARED_FILES.EMPTY') }} +
+ +Sourced from dompurify's releases.
DOMPurify 3.4.0
Most relevant changes:
- Fixed a problem with
FORBID_TAGSnot winning overADD_TAGS, thanks@kodareef5- Fixed several minor problems and typos regarding MathML attributes, thanks
@DavidOliver- Fixed
ADD_ATTR/ADD_TAGSfunction leaking into subsequent array-based calls, thanks@1Jesper1- Fixed a missing
SAFE_FOR_TEMPLATESscrub inRETURN_DOMpath, thanks@bencalif- Fixed a prototype pollution via
CUSTOM_ELEMENT_HANDLING, thanks@trace37labs- Fixed an issue with
ADD_TAGSfunction form bypassingFORBID_TAGS, thanks@eddieran- Fixed an issue with
ADD_ATTRpredicates skipping URI validation, thanks@christos-eth- Fixed an issue with
USE_PROFILESprototype pollution, thanks@christos-eth- Fixed an issue leading to possible mXSS via Re-Contextualization, thanks
@researchatfluidattacksand others- Fixed an issue with closing tags leading to possible mXSS, thanks
@frevadiscor- Fixed a problem with the type dentition patcher after Node version bump
- Fixed freezing BS runs by reducing the tested browsers array
- Bumped several dependencies where possible
- Added needed files for OpenSSF scorecard checks
Published Advisories are here: https://github.com/cure53/DOMPurify/security/advisories?state=published
DOMPurify 3.3.3
- Fixed an engine requirement for Node 20 which caused hiccups, thanks
@Rotzbua
5b16e0b
Getting 3.x branch ready for 3.4.0 release (#1250)8bcbf73
chore: Preparing 3.3.3 release5faddd6
fix: engine requirement (#1210)0f91e3a
Update README.mdd5ff1a8
Merge branch 'main' of github.com:cure53/DOMPurifyc3efd48
fix: moved back from jsdom 28 to jsdom 20988b888
fix: moved back from jsdom 28 to jsdom 202726c74
chore: Preparing 3.3.2 release6202c7e
build(deps): bump @tootallnate/once and jsdom (#1204)302b51d
fix: Expanded the regex ever so slightly to also cover scriptSourced from rack's releases.
v3.2.6
Full Changelog: https://github.com/rack/rack/compare/v3.2.5...v3.2.6
Sourced from rack's changelog.
[3.2.6] - 2026-04-01
Security
- CVE-2026-34763 Root directory disclosure via unescaped regex interpolation in
Rack::Directory.- CVE-2026-34230 Avoid O(n^2) algorithm in
Rack::Utils.select_best_encodingwhich could lead to denial of service.- CVE-2026-32762 Forwarded header semicolon injection enables Host and Scheme spoofing.
- CVE-2026-26961 Raise error for multipart requests with multiple boundary parameters.
- CVE-2026-34786
Rack::Staticheader_rulesbypass via URL-encoded path mismatch.- CVE-2026-34831
Content-Lengthmismatch inRack::Fileserror responses.- CVE-2026-34826 Multipart byte range processing allows denial of service via excessive overlapping ranges.
- CVE-2026-34835
Rack::Requestaccepts invalid Host characters, enabling host allowlist bypass.- CVE-2026-34830
Rack::Sendfileheader-basedX-Accel-Mappingregex injection enables unauthorizedX-Accel-Redirect.- CVE-2026-34785
Rack::Staticprefix matching can expose unintended files under the static root.- CVE-2026-34829 Multipart parsing without
Content-Lengthheader allows unbounded chunked file uploads.- CVE-2026-34827 Multipart header parsing allows denial of service via escape-heavy quoted parameters.
- CVE-2026-26962 Improper unfolding of folded multipart headers preserves CRLF in parsed parameter values.
e1f22fd
Bump patch version.31989fd
Fix typo in test.d268165
Fix test expectation.8f425de
Add Ruby v4.0 to the test matrix.bf83042
Drop EOL Rubies from external tests.d50c4d3
Implement OBS unfolding for multipart requests per RFC 5322 2.2.3bfb6914
Limit the number of quoted escapes during multipart parsingb3e5945
Add Content-Length size check in Rack::Multipart::Parser7a8f326
Fix root prefix bug in Rack::Statica57bc14
Only do a simple substitution on the x-accel-mapping pathsSourced from rack-session's changelog.
v2.1.2
- CVE-2026-39324 Don't fall back to unencrypted coder if encryptors are present.
504367b
Bump patch version.f43638c
Don't fall back to unencrypted coder if encryptors are present.dadcfe6
Bump actions/checkout from 4 to 5 (#54)4eb9ea8
Add top level session spec to validate existing formats.8f94577
Add rails to external tests.38ea47d
Allow the v2 encryptor to serialize messages with Marshal
(#44)43f2e3a
Fix compatibility with older Rubies.6a060b8
Support UTF-8 data when using the JSON serializer (#39)8ce0146
Fix auth_tag retrieval on JRuby (#32)7727185
Add AEAD encryption (#23)This is an HTML message with an inline image.
+
+
+
+
+------=_NextPart_001_0002--
+
+------=_NextPart_000_0001
+Content-Type: image/jpeg;
+ filename="image001.jpg"
+Content-Transfer-Encoding: base64
+Content-ID:
')
+
+ expect(helper_instance.send(:body_references_cid?, 'image001.jpg@test')).to be true
+ end
+ end
+
+ describe '#upload_inline_image' do
+ let(:mail_attachment) do
+ {
+ original: OpenStruct.new(cid: 'image001.jpg@test'),
+ blob: get_blob_for('spec/assets/avatar.png', 'image/png')
+ }
+ end
+ let(:helper_instance) { mailbox_helper_obj.new(conversation, processed_mail) }
+
+ it 'replaces percent-encoded CID references in HTML content' do
+ allow(Rails.application.routes.url_helpers).to receive(:url_for).and_return('/fake-image-url')
+ helper_instance.instance_variable_set(:@html_content, '
')
+
+ helper_instance.send(:upload_inline_image, mail_attachment)
+
+ html_content = helper_instance.instance_variable_get(:@html_content)
+ expect(html_content).to include('/fake-image-url"')
+ expect(html_content).not_to include('cid:')
+ end
+ end
+
+ describe '#add_attachments_to_message' do
+ let(:mail) { create_inbound_email_from_fixture('cid_inline_images_without_disposition.eml').mail }
+ let(:processed_mail) { MailPresenter.new(mail) }
+ let(:conversation) { create(:conversation) }
+ let(:helper_instance) { mailbox_helper_obj.new(conversation, processed_mail) }
+
+ before do
+ helper_instance.send(:create_message)
+ end
+
+ it 'detects inline image attachment by cid reference when Content-Disposition is missing' do
+ allow(Rails.application.routes.url_helpers).to receive(:url_for).and_return('/fake-image-url')
+ helper_instance.send(:add_attachments_to_message)
+
+ message = conversation.messages[0]
+
+ expect(message.attachments.count).to eq(0)
+
+ html_content = message.content_attributes[:email][:html_content][:full]
+
+ expect(html_content).to include('/fake-image-url"')
+ expect(html_content).not_to include('cid:')
+ end
+ end
end
From fe44b0714790722f4fbf70c962f3a96d5a095509 Mon Sep 17 00:00:00 2001
From: salmonumbrella <182032677+salmonumbrella@users.noreply.github.com>
Date: Wed, 6 May 2026 08:20:27 -0700
Subject: [PATCH 13/97] feat(companies): add company detail page (#14054)
---
app/javascript/dashboard/api/companies.js | 52 ++-
.../dashboard/api/specs/companies.spec.js | 142 +++----
.../Companies/CompaniesCard/CompaniesCard.vue | 52 ++-
.../Companies/CompaniesDetailsLayout.vue | 115 ++++++
.../CompaniesHeader/CompanyHeader.vue | 20 +-
.../components/CompanySortMenu.vue | 6 +
.../CompanyDetail/CompanyContactsSidebar.vue | 354 +++++++++++++++++
.../CompanyCustomAttributeItem.vue | 94 +++++
.../CompanyDetail/CompanyCustomAttributes.vue | 142 +++++++
.../CompanyDetail/CompanyProfileCard.vue | 203 ++++++++++
.../ConfirmCompanyDeleteDialog.vue | 45 +++
.../CustomAttributes/DateAttribute.vue | 2 +-
.../CustomAttributes/OtherAttribute.vue | 2 +-
.../components-next/sidebar/Sidebar.vue | 2 +-
.../i18n/locale/en/attributesMgmt.json | 8 +-
.../dashboard/i18n/locale/en/companies.json | 95 +++++
.../companies/pages/CompaniesIndex.vue | 19 +-
.../companies/pages/CompanyDetailView.vue | 236 ++++++++++++
.../routes/dashboard/companies/routes.js | 14 +
.../dashboard/settings/attributes/Index.vue | 5 +-
.../dashboard/store/modules/attributes.js | 5 +
.../modules/specs/attributes/getters.spec.js | 30 ++
app/javascript/dashboard/stores/companies.js | 358 +++++++++++++++++-
.../dashboard/stores/companies.spec.js | 213 +++++++++++
app/models/custom_attribute_definition.rb | 15 +-
config/routes.rb | 11 +
..._add_additional_attributes_to_companies.rb | 9 +
db/schema.rb | 3 +
.../accounts/companies/contacts_controller.rb | 87 +++++
.../api/v1/accounts/companies_controller.rb | 51 ++-
enterprise/app/models/company.rb | 18 +
enterprise/app/policies/company_policy.rb | 8 +
.../companies/contact_membership_service.rb | 15 +
.../accounts/companies/_company.json.jbuilder | 8 -
.../accounts/companies/avatar.json.jbuilder | 3 +
.../companies/contacts/_contact.json.jbuilder | 10 +
.../companies/contacts/create.json.jbuilder | 3 +
.../companies/contacts/index.json.jbuilder | 10 +
.../companies/contacts/search.json.jbuilder | 10 +
.../accounts/companies/create.json.jbuilder | 2 +-
.../destroy_custom_attributes.json.jbuilder | 3 +
.../v1/accounts/companies/index.json.jbuilder | 2 +-
.../accounts/companies/search.json.jbuilder | 2 +-
.../v1/accounts/companies/show.json.jbuilder | 2 +-
.../accounts/companies/update.json.jbuilder | 2 +-
.../api/v1/models/_company.json.jbuilder | 10 +
.../companies/contacts_controller_spec.rb | 78 ++++
.../v1/accounts/companies_controller_spec.rb | 67 ++++
.../custom_attribute_definition_spec.rb | 11 +
49 files changed, 2461 insertions(+), 193 deletions(-)
create mode 100644 app/javascript/dashboard/components-next/Companies/CompaniesDetailsLayout.vue
create mode 100644 app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyContactsSidebar.vue
create mode 100644 app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyCustomAttributeItem.vue
create mode 100644 app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyCustomAttributes.vue
create mode 100644 app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyProfileCard.vue
create mode 100644 app/javascript/dashboard/components-next/Companies/CompanyDetail/ConfirmCompanyDeleteDialog.vue
create mode 100644 app/javascript/dashboard/routes/dashboard/companies/pages/CompanyDetailView.vue
create mode 100644 app/javascript/dashboard/stores/companies.spec.js
create mode 100644 db/migrate/20260422133000_add_additional_attributes_to_companies.rb
create mode 100644 enterprise/app/controllers/api/v1/accounts/companies/contacts_controller.rb
create mode 100644 enterprise/app/services/companies/contact_membership_service.rb
delete mode 100644 enterprise/app/views/api/v1/accounts/companies/_company.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/accounts/companies/avatar.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/accounts/companies/contacts/_contact.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/accounts/companies/contacts/create.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/accounts/companies/contacts/index.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/accounts/companies/contacts/search.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/accounts/companies/destroy_custom_attributes.json.jbuilder
create mode 100644 enterprise/app/views/api/v1/models/_company.json.jbuilder
create mode 100644 spec/enterprise/controllers/api/v1/accounts/companies/contacts_controller_spec.rb
diff --git a/app/javascript/dashboard/api/companies.js b/app/javascript/dashboard/api/companies.js
index 090b530c4..b98a59983 100644
--- a/app/javascript/dashboard/api/companies.js
+++ b/app/javascript/dashboard/api/companies.js
@@ -1,21 +1,12 @@
/* global axios */
import ApiClient from './ApiClient';
-export const buildCompanyParams = (page, sort) => {
- let params = `page=${page}`;
- if (sort) {
- params = `${params}&sort=${sort}`;
- }
- return params;
-};
-
-export const buildSearchParams = (query, page, sort) => {
- let params = `q=${encodeURIComponent(query)}&page=${page}`;
- if (sort) {
- params = `${params}&sort=${sort}`;
- }
- return params;
-};
+const buildParams = params =>
+ new URLSearchParams(
+ Object.entries(params).filter(
+ ([key, value]) => value !== undefined && (value !== '' || key === 'q')
+ )
+ ).toString();
class CompanyAPI extends ApiClient {
constructor() {
@@ -24,14 +15,41 @@ class CompanyAPI extends ApiClient {
get(params = {}) {
const { page = 1, sort = 'name' } = params;
- const requestURL = `${this.url}?${buildCompanyParams(page, sort)}`;
+ const requestURL = `${this.url}?${buildParams({ page, sort })}`;
return axios.get(requestURL);
}
search(query = '', page = 1, sort = 'name') {
- const requestURL = `${this.url}/search?${buildSearchParams(query, page, sort)}`;
+ const requestURL = `${this.url}/search?${buildParams({ q: query, page, sort })}`;
return axios.get(requestURL);
}
+
+ listContacts(id, page = 1) {
+ return axios.get(`${this.url}/${id}/contacts?${buildParams({ page })}`);
+ }
+
+ searchContacts(id, query = '', page = 1) {
+ const requestURL = `${this.url}/${id}/contacts/search?${buildParams({ q: query, page })}`;
+ return axios.get(requestURL);
+ }
+
+ createContact(id, payload) {
+ return axios.post(`${this.url}/${id}/contacts`, payload);
+ }
+
+ removeContact(id, contactId) {
+ return axios.delete(`${this.url}/${id}/contacts/${contactId}`);
+ }
+
+ destroyCustomAttributes(id, customAttributes) {
+ return axios.post(`${this.url}/${id}/destroy_custom_attributes`, {
+ custom_attributes: customAttributes,
+ });
+ }
+
+ destroyAvatar(id) {
+ return axios.delete(`${this.url}/${id}/avatar`);
+ }
}
export default new CompanyAPI();
diff --git a/app/javascript/dashboard/api/specs/companies.spec.js b/app/javascript/dashboard/api/specs/companies.spec.js
index 82fdc1c97..ca1d905de 100644
--- a/app/javascript/dashboard/api/specs/companies.spec.js
+++ b/app/javascript/dashboard/api/specs/companies.spec.js
@@ -1,7 +1,4 @@
-import companyAPI, {
- buildCompanyParams,
- buildSearchParams,
-} from '../companies';
+import companyAPI from '../companies';
import ApiClient from '../ApiClient';
describe('#CompanyAPI', () => {
@@ -9,7 +6,6 @@ describe('#CompanyAPI', () => {
expect(companyAPI).toBeInstanceOf(ApiClient);
expect(companyAPI).toHaveProperty('get');
expect(companyAPI).toHaveProperty('show');
- expect(companyAPI).toHaveProperty('create');
expect(companyAPI).toHaveProperty('update');
expect(companyAPI).toHaveProperty('delete');
expect(companyAPI).toHaveProperty('search');
@@ -32,111 +28,69 @@ describe('#CompanyAPI', () => {
window.axios = originalAxios;
});
- it('#get with default params', () => {
+ it('#get includes pagination and sorting params', () => {
companyAPI.get({});
expect(axiosMock.get).toHaveBeenCalledWith(
'/api/v1/companies?page=1&sort=name'
);
});
- it('#get with page and sort params', () => {
- companyAPI.get({ page: 2, sort: 'domain' });
- expect(axiosMock.get).toHaveBeenCalledWith(
- '/api/v1/companies?page=2&sort=domain'
- );
- });
-
- it('#get with descending sort', () => {
- companyAPI.get({ page: 1, sort: '-created_at' });
- expect(axiosMock.get).toHaveBeenCalledWith(
- '/api/v1/companies?page=1&sort=-created_at'
- );
- });
-
- it('#search with query', () => {
- companyAPI.search('acme', 1, 'name');
- expect(axiosMock.get).toHaveBeenCalledWith(
- '/api/v1/companies/search?q=acme&page=1&sort=name'
- );
- });
-
- it('#search with special characters in query', () => {
+ it('#search encodes query params', () => {
companyAPI.search('acme & co', 2, 'domain');
expect(axiosMock.get).toHaveBeenCalledWith(
- '/api/v1/companies/search?q=acme%20%26%20co&page=2&sort=domain'
+ '/api/v1/companies/search?q=acme+%26+co&page=2&sort=domain'
);
});
- it('#search with descending sort', () => {
- companyAPI.search('test', 1, '-created_at');
- expect(axiosMock.get).toHaveBeenCalledWith(
- '/api/v1/companies/search?q=test&page=1&sort=-created_at'
- );
- });
-
- it('#search with empty query', () => {
+ it('#search keeps empty query param for backend validation', () => {
companyAPI.search('', 1, 'name');
expect(axiosMock.get).toHaveBeenCalledWith(
'/api/v1/companies/search?q=&page=1&sort=name'
);
});
- });
-});
-describe('#buildCompanyParams', () => {
- it('returns correct string with page only', () => {
- expect(buildCompanyParams(1)).toBe('page=1');
- });
-
- it('returns correct string with page and sort', () => {
- expect(buildCompanyParams(1, 'name')).toBe('page=1&sort=name');
- });
-
- it('returns correct string with different page', () => {
- expect(buildCompanyParams(3, 'domain')).toBe('page=3&sort=domain');
- });
-
- it('returns correct string with descending sort', () => {
- expect(buildCompanyParams(1, '-created_at')).toBe(
- 'page=1&sort=-created_at'
- );
- });
-
- it('returns correct string without sort parameter', () => {
- expect(buildCompanyParams(2, '')).toBe('page=2');
- });
-});
-
-describe('#buildSearchParams', () => {
- it('returns correct string with all parameters', () => {
- expect(buildSearchParams('acme', 1, 'name')).toBe(
- 'q=acme&page=1&sort=name'
- );
- });
-
- it('returns correct string with special characters', () => {
- expect(buildSearchParams('acme & co', 2, 'domain')).toBe(
- 'q=acme%20%26%20co&page=2&sort=domain'
- );
- });
-
- it('returns correct string with empty query', () => {
- expect(buildSearchParams('', 1, 'name')).toBe('q=&page=1&sort=name');
- });
-
- it('returns correct string without sort parameter', () => {
- expect(buildSearchParams('test', 1, '')).toBe('q=test&page=1');
- });
-
- it('returns correct string with descending sort', () => {
- expect(buildSearchParams('company', 3, '-created_at')).toBe(
- 'q=company&page=3&sort=-created_at'
- );
- });
-
- it('encodes special characters correctly', () => {
- expect(buildSearchParams('test@example.com', 1, 'name')).toBe(
- 'q=test%40example.com&page=1&sort=name'
- );
+ it('#destroyAvatar deletes the company avatar endpoint', () => {
+ companyAPI.destroyAvatar(1);
+ expect(axiosMock.delete).toHaveBeenCalledWith(
+ '/api/v1/companies/1/avatar'
+ );
+ });
+
+ it('#listContacts fetches company contacts', () => {
+ companyAPI.listContacts(1, 2);
+ expect(axiosMock.get).toHaveBeenCalledWith(
+ '/api/v1/companies/1/contacts?page=2'
+ );
+ });
+
+ it('#searchContacts encodes contact search params', () => {
+ companyAPI.searchContacts(1, 'jane & co', 3);
+ expect(axiosMock.get).toHaveBeenCalledWith(
+ '/api/v1/companies/1/contacts/search?q=jane+%26+co&page=3'
+ );
+ });
+
+ it('#createContact links a contact to the company', () => {
+ companyAPI.createContact(1, { contact_id: 2 });
+ expect(axiosMock.post).toHaveBeenCalledWith(
+ '/api/v1/companies/1/contacts',
+ { contact_id: 2 }
+ );
+ });
+
+ it('#removeContact unlinks a contact from the company', () => {
+ companyAPI.removeContact(1, 2);
+ expect(axiosMock.delete).toHaveBeenCalledWith(
+ '/api/v1/companies/1/contacts/2'
+ );
+ });
+
+ it('#destroyCustomAttributes removes company custom attributes', () => {
+ companyAPI.destroyCustomAttributes(1, ['plan']);
+ expect(axiosMock.post).toHaveBeenCalledWith(
+ '/api/v1/companies/1/destroy_custom_attributes',
+ { custom_attributes: ['plan'] }
+ );
+ });
});
});
diff --git a/app/javascript/dashboard/components-next/Companies/CompaniesCard/CompaniesCard.vue b/app/javascript/dashboard/components-next/Companies/CompaniesCard/CompaniesCard.vue
index 4603521eb..fe4385bbb 100644
--- a/app/javascript/dashboard/components-next/Companies/CompaniesCard/CompaniesCard.vue
+++ b/app/javascript/dashboard/components-next/Companies/CompaniesCard/CompaniesCard.vue
@@ -1,7 +1,7 @@
+ {{ contactMeta(contact) }} +
++ {{ t('COMPANIES.DETAIL.ATTRIBUTES.NO_ATTRIBUTES') }} +
++ {{ t('COMPANIES.DETAIL.ATTRIBUTES.EMPTY_STATE') }} +
+ diff --git a/app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyProfileCard.vue b/app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyProfileCard.vue new file mode 100644 index 000000000..1ffbf0c18 --- /dev/null +++ b/app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyProfileCard.vue @@ -0,0 +1,203 @@ + + + ++ {{ t('COMPANIES.DETAIL.AVATAR.UPDATING') }} +
++ {{ t('COMPANIES.DETAIL.EMPTY_STATE.SUBTITLE') }} +
+{{ $t('BULK_ACTION.AGENT_LIST_LOADING') }}
-- {{ - $t('BULK_ACTION.ASSIGN_CONFIRMATION_LABEL', { - conversationCount, - conversationLabel, - }) - }} - - {{ selectedAgent.name }} - - ? -
-- {{ - $t('BULK_ACTION.UNASSIGN_CONFIRMATION_LABEL', { - conversationCount, - conversationLabel, - }) - }} -
-{initial_code} {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
From cc612e755b5bda1bfe67d478c62798a19f3147b5 Mon Sep 17 00:00:00 2001
From: Shivam Mishra + {{ t('COMPANIES.DETAIL.HISTORY.EMPTY') }} +
+ diff --git a/app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyNotesSidebar.vue b/app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyNotesSidebar.vue new file mode 100644 index 000000000..234e0cd12 --- /dev/null +++ b/app/javascript/dashboard/components-next/Companies/CompanyDetail/CompanyNotesSidebar.vue @@ -0,0 +1,114 @@ + + + ++ {{ t('COMPANIES.DETAIL.NOTES.EMPTY') }} +
+ diff --git a/app/javascript/dashboard/i18n/locale/en/companies.json b/app/javascript/dashboard/i18n/locale/en/companies.json index 1fe8bc169..534205038 100644 --- a/app/javascript/dashboard/i18n/locale/en/companies.json +++ b/app/javascript/dashboard/i18n/locale/en/companies.json @@ -44,9 +44,17 @@ "SIDEBAR": { "TABS": { "ATTRIBUTES": "Attributes", - "CONTACTS": "Contacts" + "CONTACTS": "Contacts", + "HISTORY": "History", + "NOTES": "Notes" } }, + "HISTORY": { + "EMPTY": "No conversations found for this company's contacts yet." + }, + "NOTES": { + "EMPTY": "No notes found for this company's contacts yet." + }, "ATTRIBUTES": { "SEARCH_PLACEHOLDER": "Search attributes...", "EMPTY_STATE": "There are no company custom attributes configured yet.", diff --git a/app/javascript/dashboard/routes/dashboard/companies/pages/CompanyDetailView.vue b/app/javascript/dashboard/routes/dashboard/companies/pages/CompanyDetailView.vue index 313df49d3..86627f952 100644 --- a/app/javascript/dashboard/routes/dashboard/companies/pages/CompanyDetailView.vue +++ b/app/javascript/dashboard/routes/dashboard/companies/pages/CompanyDetailView.vue @@ -8,7 +8,10 @@ import Policy from 'dashboard/components/policy.vue'; import Button from 'dashboard/components-next/button/Button.vue'; import CompaniesDetailsLayout from 'dashboard/components-next/Companies/CompaniesDetailsLayout.vue'; import Spinner from 'dashboard/components-next/spinner/Spinner.vue'; +import TabBar from 'dashboard/components-next/tabbar/TabBar.vue'; import CompanyContactsSidebar from 'dashboard/components-next/Companies/CompanyDetail/CompanyContactsSidebar.vue'; +import CompanyHistorySidebar from 'dashboard/components-next/Companies/CompanyDetail/CompanyHistorySidebar.vue'; +import CompanyNotesSidebar from 'dashboard/components-next/Companies/CompanyDetail/CompanyNotesSidebar.vue'; import CompanyProfileCard from 'dashboard/components-next/Companies/CompanyDetail/CompanyProfileCard.vue'; import ConfirmCompanyDeleteDialog from 'dashboard/components-next/Companies/CompanyDetail/ConfirmCompanyDeleteDialog.vue'; import { useCompaniesStore } from 'dashboard/stores/companies'; @@ -20,11 +23,16 @@ const { t } = useI18n(); const confirmDeleteDialogRef = ref(null); const selectedCandidate = ref(null); +const activeSidebarTab = ref('history'); const companyId = computed(() => Number(route.params.companyId)); const company = computed(() => companiesStore.getRecord(companyId.value)); const companyContacts = computed(() => companiesStore.companyContacts); const companyContactsMeta = computed(() => companiesStore.companyContactsMeta); +const companyConversations = computed( + () => companiesStore.companyConversations || [] +); +const companyNotes = computed(() => companiesStore.companyNotes || []); const contactSearchResults = computed( () => companiesStore.contactSearchResults ); @@ -32,6 +40,10 @@ const uiFlags = computed(() => companiesStore.getUIFlags); const isFetchingCompany = computed(() => uiFlags.value.fetchingItem); const isFetchingContacts = computed(() => uiFlags.value.fetchingContacts); +const isFetchingConversations = computed( + () => uiFlags.value.fetchingConversations +); +const isFetchingNotes = computed(() => uiFlags.value.fetchingNotes); const isSearchingContacts = computed(() => uiFlags.value.searchingContacts); const isManagingContacts = computed( () => uiFlags.value.creatingContact || uiFlags.value.removingContact @@ -50,6 +62,27 @@ const breadcrumbItems = computed(() => [ : []), ]); +const SIDEBAR_TABS_OPTIONS = [ + { key: 'HISTORY', value: 'history' }, + { key: 'NOTES', value: 'notes' }, + { key: 'CONTACTS', value: 'contacts' }, +]; + +const sidebarTabs = computed(() => + SIDEBAR_TABS_OPTIONS.map(tab => ({ + label: { + notes: t('COMPANIES.DETAIL.SIDEBAR.TABS.NOTES'), + history: t('COMPANIES.DETAIL.SIDEBAR.TABS.HISTORY'), + contacts: `${t('COMPANIES.DETAIL.SIDEBAR.TABS.CONTACTS')} (${Number(companyContactsMeta.value.totalCount || 0)})`, + }[tab.value], + value: tab.value, + })) +); + +const activeSidebarTabIndex = computed(() => + SIDEBAR_TABS_OPTIONS.findIndex(tab => tab.value === activeSidebarTab.value) +); + const goToCompaniesIndex = () => { router.push({ name: 'companies_dashboard_index', @@ -79,6 +112,19 @@ const clearSelectedCandidate = () => { selectedCandidate.value = null; }; +const loadSidebarTab = tab => { + if (!companyId.value) return; + if (tab === 'notes') companiesStore.getCompanyNotes(companyId.value); + if (tab === 'history') { + companiesStore.getCompanyConversations(companyId.value); + } +}; + +const handleSidebarTabChange = tab => { + activeSidebarTab.value = tab.value; + loadSidebarTab(tab.value); +}; + const handleContactSearch = async query => { await companiesStore.searchCompanyContactCandidates({ companyId: companyId.value, @@ -143,10 +189,12 @@ watch( async id => { companiesStore.resetCompanyDetailState(); clearSelectedCandidate(); + activeSidebarTab.value = 'history'; if (!id) return; await Promise.allSettled([ companiesStore.show(id), companiesStore.getCompanyContacts(id), + companiesStore.getCompanyConversations(id), ]); }, { immediate: true } @@ -207,8 +255,29 @@ onBeforeUnmount(() => {Sourced from nokogiri's releases.
v1.19.3 / 2026-04-27
Fixed / Security
- Address exponential regex backtracking in CSS selector tokenizer. See GHSA-c4rq-3m3g-8wgx for more information.
- [CRuby] Address memory leak in
XSLT::Stylesheet#transform. See GHSA-v2fc-qm4h-8hqv for more information.46b89e5d7b9e844c2ee360794240c6ea2a4e6fa0c5892a4ed487db621224b639 nokogiri-1.19.3-aarch64-linux-gnu.gem 8392dfdcd21be7a94dbbe9ccc138dea01b97b24cb2dc02a114ca98bfb1d9a0b7 nokogiri-1.19.3-aarch64-linux-musl.gem 3919d5ffc334ad778a4a9eb88fda7dcb8b1fb58c8a52ac640c6dcd2f038e774f nokogiri-1.19.3-arm-linux-gnu.gem 9ce1cb6346bb9c67b1550eb537aa183ead91e4b6eadb2f36ade02d8dd2a79fb6 nokogiri-1.19.3-arm-linux-musl.gem 71b9bd424b1b7abc18b05052a1a3cfd3627abdca62be280854cc411791357e42 nokogiri-1.19.3-arm64-darwin.gem 40ea6ebf5cf2005dae1dee26dd557d3afb41fb6de6c9764aca8cf06fdb841db1 nokogiri-1.19.3-java.gem 8bb7132cad356c879a1286eaabcb5e68326cb2490317984280fbc62f456d506a nokogiri-1.19.3-x64-mingw-ucrt.gem 77f3fba57d46c53ab31e62fc6c28f705109d1bf6264356c76f132b2be5728d4d nokogiri-1.19.3-x86_64-darwin.gem 2f5078620fe12e83669b5b17311b32532a8153d02eee7ad06948b926d6080976 nokogiri-1.19.3-x86_64-linux-gnu.gem 248c906d2166eca5efb56d52fdee5f9a1f51d69a72e2b64fdac647b4ce39ea3f nokogiri-1.19.3-x86_64-linux-musl.gem 78312cbac32a40c812780d9678221b79d51288eec00054c1a8d15f7ce05960e8 nokogiri-1.19.3.gemv1.19.2 / 2026-03-19
Dependencies
- [JRuby] Saxon-HE is updated to 12.7, from 9.6.0-4. Saxon-HE is a transitive dependency of nu.validator:jing, and this update addresses CVEs in Saxon-HE's own transitive dependencies JDOM and dom4j. We don't think this warrants a security release, however we're cutting a patch release to help users whose security scanners are flagging this. #3611
@flavorjonesSHA256 Checksums
c34d5c8208025587554608e98fd88ab125b29c80f9352b821964e9a5d5cfbd19 nokogiri-1.19.2-aarch64-linux-gnu.gem 7f6b4b0202d507326841a4f790294bf75098aef50c7173443812e3ac5cb06515 nokogiri-1.19.2-aarch64-linux-musl.gem b7fa1139016f3dc850bda1260988f0d749934a939d04ef2da13bec060d7d5081 nokogiri-1.19.2-arm-linux-gnu.gem 61114d44f6742ff72194a1b3020967201e2eb982814778d130f6471c11f9828c nokogiri-1.19.2-arm-linux-musl.gem 58d8ea2e31a967b843b70487a44c14c8ba1866daa1b9da9be9dbdf1b43dee205 nokogiri-1.19.2-arm64-darwin.gem e9d67034bc80ca71043040beea8a91be5dc99b662daa38a2bfb361b7a2cc8717 nokogiri-1.19.2-java.gem 8ccf25eea3363a2c7b3f2e173a3400582c633cfead27f805df9a9c56d4852d1a nokogiri-1.19.2-x64-mingw-ucrt.gem 7d9af11fda72dfaa2961d8c4d5380ca0b51bc389dc5f8d4b859b9644f195e7a4 nokogiri-1.19.2-x86_64-darwin.gem fa8feca882b73e871a9845f3817a72e9734c8e974bdc4fbad6e4bc6e8076b94f nokogiri-1.19.2-x86_64-linux-gnu.gem 93128448e61a9383a30baef041bf1f5817e22f297a1d400521e90294445069a8 nokogiri-1.19.2-x86_64-linux-musl.gem 38fdd8b59db3d5ea9e7dfb14702e882b9bf819198d5bf976f17ebce12c481756 nokogiri-1.19.2.gemFull Changelog: https://github.com/sparklemotion/nokogiri/compare/v1.19.1...v1.19.2
Sourced from nokogiri's changelog.
v1.19.3 / 2026-04-27
Fixed / Security
- Address exponential regex backtracking in CSS selector tokenizer. See GHSA-c4rq-3m3g-8wgx for more information.
- [CRuby] Address memory leak in
XSLT::Stylesheet#transform. See GHSA-v2fc-qm4h-8hqv for more information.v1.19.2 / 2026-03-19
Dependencies
- [JRuby] Saxon-HE is updated to 12.7, from 9.6.0-4. Saxon-HE is a transitive dependency of nu.validator:jing, and this update addresses CVEs in Saxon-HE's own transitive dependencies JDOM and dom4j. We don't think this warrants a security release, however we're cutting a patch release to help users whose security scanners are flagging this. #3611
@flavorjones
c139a3d
version bump to v1.19.37501a63
fix: backtracking in CSS tokenizer rules (v1.19.x backport) (#3627)03e7968
test: skip CSS tokenizer benchmarks on JRubyb984b7e
fix: ReDoS in CSS tokenizer ident rule0092623
fix: ReDoS in CSS tokenizer STRING ruleee17d33
fix: memory leak in XSLT transform (backport to v1.19.x) (#3624)ce188a3
doc: update CHANGELOGcaeaac4
fix: memory leak in XSLT transform25220bf
dep(test): test against libxml-ruby v6 (#3618)0caeb21
doc: add security warnings for untrusted XSLT stylesheets