Compare commits

...
Author SHA1 Message Date
speakeasy-github[bot]andspeakeasy-bot 57f3b0e394 empty commit to trigger [run-tests] workflow 2026-06-19 01:06:27 +00:00
speakeasybot 0b6f0086aa ## Python SDK Changes:
* `open_router.benchmarks.get_benchmarks()`: **Added**
* `open_router.datasets.get_benchmarks_artificial_analysis()`: **Deleted** **Breaking** ⚠️
* `open_router.datasets.get_benchmarks_design_arena()`: **Deleted** **Breaking** ⚠️
* `open_router.chat.send()`:  `response` **Changed**
* `open_router.embeddings.list_models()`:  `response.data.[].reasoning` **Added**
* `open_router.models.get()`:  `response.data.reasoning` **Added**
* `open_router.models.list()`:  `response.data.[].reasoning` **Added**
* `open_router.models.list_for_user()`:  `response.data.[].reasoning` **Added**
2026-06-19 01:06:11 +00:00
14a62e3451 chore: update OpenAPI spec from monorepo (#339)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-18 16:24:52 -07:00
7e29e408af chore: update OpenAPI spec from monorepo (#333)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-18 10:20:41 -07:00
Christine ChenandGitHub 30bc131b97 feat: auto-merge Speakeasy SDK generation PRs (#332) 2026-06-18 11:05:15 -04:00
Christine Chen 1b0118c365 fix: address review feedback on auto-merge workflow
Pipe gh pr list output through jq instead of passing --arg to gh --jq,
and add a repo-level concurrency group to prevent cross-PR merge races.
2026-06-17 16:54:40 -04:00
Christine Chen cda73e5ebf feat: auto-merge Speakeasy SDK generation PRs
Add a workflow that merges Speakeasy codegen PRs when the bot applies a
semver label, closing superseded regen PRs first. This unblocks
sdk_publish.yaml after mode:pr generation without manual intervention.
2026-06-17 16:28:01 -04:00
b0eda78d3f chore: update OpenAPI spec from monorepo (#330)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-17 12:53:02 -07:00
Christine ChenandGitHub bf682bdb62 fix: use PR mode for spec-change SDK generation (#329) 2026-06-17 15:07:36 -04:00
Christine Chen b322622117 fix: use PR mode for spec-change SDK generation
Switch sdk_generation_for_spec_change.yaml from direct to pr mode so
Speakeasy opens a PR instead of pushing to main. This avoids branch
protection failures and routes publishing through sdk_publish.yaml.
2026-06-17 10:37:08 -04:00
Matt AppersonandGitHub 415450e785 chore: 🐝 Update SDK - Generate 0.10.0 (#317) 2026-06-17 09:48:04 -04:00
speakeasy-github[bot]andspeakeasy-bot 1d488f0117 empty commit to trigger [run-tests] workflow 2026-06-17 01:01:27 +00:00
speakeasybot 4e789208b4 ## Python SDK Changes:
* `open_router.beta.responses.send()`: 
  *  `request` **Changed** **Breaking** ⚠️
  *  `response` **Changed** **Breaking** ⚠️
* `open_router.presets.create_presets_responses()`:  `request` **Changed** **Breaking** ⚠️
* `open_router.presets.create_presets_chat_completions()`:  `request` **Changed** **Breaking** ⚠️
* `open_router.chat.send()`:  `request` **Changed** **Breaking** ⚠️
* `open_router.workspaces.set_budget()`: **Added**
* `open_router.o_auth.create_auth_code()`: 
  *  `request.workspace_id` **Added**
  *  `error.status[403]` **Added**
* `open_router.files.download()`: **Added**
* `open_router.models.get()`: **Added**
* `open_router.workspaces.list_budgets()`: **Added**
* `open_router.workspaces.delete_budget()`: **Added**
* `open_router.datasets.get_benchmarks_artificial_analysis()`: **Added**
* `open_router.beta.analytics.query_analytics()`:  `response.data.warnings` **Added**
* `open_router.files.delete()`: **Added**
* `open_router.files.retrieve()`: **Added**
* `open_router.files.upload()`: **Added**
* `open_router.embeddings.list_models()`:  `response.data.[].benchmarks` **Added**
* `open_router.models.list()`: 
  *  `request` **Changed**
  *  `response.data.[].benchmarks` **Added**
* `open_router.models.list_for_user()`:  `response.data.[].benchmarks` **Added**
* `open_router.files.list()`: **Added**
* `open_router.presets.create_presets_messages()`:  `request` **Changed**
* `open_router.datasets.get_benchmarks_design_arena()`: **Added**
2026-06-17 01:01:09 +00:00
cdd4dc7302 chore: update OpenAPI spec from monorepo (#328)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-16 16:01:05 -07:00
Christine ChenandGitHub 60708e1e8b docs: remove beta labels from Python SDK README (#327) 2026-06-16 18:58:58 -04:00
Christine Chen 5a324f99ae docs: remove beta labels from Python SDK README
The Python SDK is no longer in beta. Drop the (Beta) title suffix and
remove the Maturity section disclaimer from README and README-PYPI.

SDK-464
2026-06-16 18:09:12 -04:00
d5778dfafb chore: update OpenAPI spec from monorepo (#326)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-16 14:36:02 -07:00
68c251830c chore: update OpenAPI spec from monorepo (#325)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-16 12:52:37 -07:00
2aa2d73d2d chore: update OpenAPI spec from monorepo (#324)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-16 10:37:39 -07:00
58bd390fbd chore: update OpenAPI spec from monorepo (#323)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-16 00:39:20 -07:00
2707901239 chore: update OpenAPI spec from monorepo (#322)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-15 14:21:32 -07:00
a5ed2de8a8 chore: update OpenAPI spec from monorepo (#321)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-15 10:29:12 -07:00
robert-j-yandGitHub 21893dda58 ci: regenerate SDK directly when merged spec changes land (#315) 2026-06-15 09:52:12 -07:00
758a2f3d49 chore: update OpenAPI spec from monorepo (#320)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-15 09:28:46 -07:00
0331f14f19 chore: update OpenAPI spec from monorepo (#319)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-15 06:48:08 -07:00
138b131a35 chore: update OpenAPI spec from monorepo (#318)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 22:08:18 -07:00
Christine ChenandGitHub 55c0d5c7fd docs: update outdated model counts in SDK documentation (#313) 2026-06-12 17:37:19 -04:00
e98a7a8260 chore: update OpenAPI spec from monorepo (#316)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 13:38:51 -07:00
Christine Chen 7e7787cb23 docs: update outdated model counts in SDK documentation
Refresh README and overview copy to reflect 400+ available models instead of 300+.
2026-06-12 15:47:18 -04:00
c4b508f045 chore: update OpenAPI spec from monorepo (#314)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 12:44:30 -07:00
52e7853d21 chore: update OpenAPI spec from monorepo (#312)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 10:46:58 -07:00
d43061f722 chore: update OpenAPI spec from monorepo (#311)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 10:09:55 -07:00
7b10fd47d8 chore: update OpenAPI spec from monorepo (#310)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 07:28:06 -07:00
95f2c87bfa chore: update OpenAPI spec from monorepo (#309)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-12 06:51:21 -07:00
c756fc51e0 chore: update OpenAPI spec from monorepo (#308)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-11 17:50:16 -07:00
386db75669 chore: update OpenAPI spec from monorepo (#307)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-11 13:27:05 -07:00
e3dc2e6f4c chore: update OpenAPI spec from monorepo (#306)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-11 12:10:20 -07:00
70c8757fc0 chore: update OpenAPI spec from monorepo (#305)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-11 11:10:32 -07:00
b794150ed9 chore: update OpenAPI spec from monorepo (#304)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-11 09:18:46 -07:00
github-actions[bot]GitHubspeakeasybotspeakeasy-github[bot] <128539517+speakeasy-github[bot]@users.noreply.github.com>
0f116c9792 chore: 🐝 Update SDK - Generate 0.9.2 (#205)
Co-authored-by: speakeasybot <bot@speakeasyapi.dev>
Co-authored-by: speakeasy-github[bot] <128539517+speakeasy-github[bot]@users.noreply.github.com>
2026-06-11 12:10:31 -04:00
0c735989c1 chore: update OpenAPI spec from monorepo (#303)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-10 22:01:22 -07:00
3b2f5b2316 chore: update OpenAPI spec from monorepo (#301)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-10 16:46:14 -07:00
3883438f02 chore: update OpenAPI spec from monorepo (#300)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-10 16:00:58 -07:00
1cd1e66e2d chore: update OpenAPI spec from monorepo (#299)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-10 11:13:43 -07:00
f29a61de7e chore: update OpenAPI spec from monorepo (#298)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-10 10:06:09 -07:00
1725abad89 chore: update OpenAPI spec from monorepo (#297)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-10 06:22:51 -07:00
8df520997d chore: update OpenAPI spec from monorepo (#296)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-09 19:48:29 -07:00
c4843278fd chore: update OpenAPI spec from monorepo (#295)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-09 17:13:15 -07:00
ccbd6d16f8 chore: update OpenAPI spec from monorepo (#294)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-09 16:50:55 -07:00
80646bd8a6 chore: update OpenAPI spec from monorepo (#293)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-09 15:54:33 -07:00
68fc6f0ee9 chore: update OpenAPI spec from monorepo (#292)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-09 12:37:51 -07:00
23ee599564 chore: update OpenAPI spec from monorepo (#291)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-09 11:13:04 -07:00
2203de96b4 chore: update OpenAPI spec from monorepo (#290)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-08 16:40:27 -04:00
b7d5098042 chore: update OpenAPI spec from monorepo (#289)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-08 12:07:59 -04:00
b9f588d84b chore: update OpenAPI spec from monorepo (#288)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-08 10:28:12 -04:00
5caa85a52c chore: update OpenAPI spec from monorepo (#287)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-05 10:37:07 -04:00
fc328cd45d chore: update OpenAPI spec from monorepo (#286)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-04 16:17:54 -04:00
234901509f chore: update OpenAPI spec from monorepo (#285)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-03 16:57:01 -04:00
771a5b1a52 chore: update OpenAPI spec from monorepo (#284)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-06-01 20:54:31 -07:00
93dd1b59fd chore: update OpenAPI spec from monorepo (#282)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-29 17:59:39 -07:00
698e7d6d7e chore: update OpenAPI spec from monorepo (#281)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-29 15:52:56 -07:00
fe4080dfda chore: update OpenAPI spec from monorepo (#280)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-28 14:04:37 -07:00
1090ab30b2 chore: update OpenAPI spec from monorepo (#279)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-28 10:52:41 -07:00
51a8873f33 chore: update OpenAPI spec from monorepo (#278)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-28 08:22:21 -07:00
a95178f8b3 chore: update OpenAPI spec from monorepo (#277)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-28 03:20:57 -07:00
63b73f57d4 chore: update OpenAPI spec from monorepo (#276)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-27 23:21:46 -07:00
6ceb25ca84 chore: update OpenAPI spec from monorepo (#275)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-26 20:08:49 -07:00
b5aca7806b chore: update OpenAPI spec from monorepo (#274)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-26 17:38:30 -07:00
4610ea4719 chore: update OpenAPI spec from monorepo (#273)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-26 14:05:37 -07:00
67bd50597a chore: update OpenAPI spec from monorepo (#272)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-26 06:46:07 -07:00
859e89d545 chore: update OpenAPI spec from monorepo (#271)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-24 04:32:12 -07:00
f94fcc1eb1 chore: update OpenAPI spec from monorepo (#270)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-22 18:00:36 -07:00
c361f61f5b chore: update OpenAPI spec from monorepo (#268)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-22 09:44:53 -07:00
f119275b26 chore: update OpenAPI spec from monorepo (#267)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-20 14:45:06 -07:00
460658428f chore: update OpenAPI spec from monorepo (#263)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-19 17:32:47 -07:00
5d441447a9 chore: update OpenAPI spec from monorepo (#262)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-19 14:12:00 -07:00
d549103228 chore: update OpenAPI spec from monorepo (#261)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-19 12:50:36 -07:00
Matt AppersonandGitHub 3e77e61a5c chore: bump speakeasy version to 1.763.2 (#260) 2026-05-19 15:18:43 -04:00
e0dddac466 chore: update OpenAPI spec from monorepo (#259)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-18 22:55:48 -07:00
32c6c506cf chore: update OpenAPI spec from monorepo (#258)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-18 17:30:34 -07:00
59a8775ed7 chore: update OpenAPI spec from monorepo (#257)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-18 15:36:40 -07:00
e7a06917b2 chore: update OpenAPI spec from monorepo (#256)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-16 20:34:21 -07:00
d8c617dfd2 chore: update OpenAPI spec from monorepo (#255)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-16 18:53:40 -07:00
752156a9ad chore: update OpenAPI spec from monorepo (#254)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-16 14:13:23 -07:00
688c063276 chore: update OpenAPI spec from monorepo (#253)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-16 11:20:24 -07:00
da19555f7f chore: update OpenAPI spec from monorepo (#252)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-15 16:01:52 -07:00
0ecf2ef253 chore: update OpenAPI spec from monorepo (#251)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-15 13:49:07 -07:00
a7fd661299 chore: update OpenAPI spec from monorepo (#250)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-15 11:26:30 -07:00
c5e2532cc4 chore: update OpenAPI spec from monorepo (#249)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-15 06:27:29 -07:00
0aa6eabffd chore: update OpenAPI spec from monorepo (#248)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-14 17:00:01 -07:00
205749ae6b chore: update OpenAPI spec from monorepo (#247)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-14 13:13:22 -07:00
bf8a2c6adc chore: update OpenAPI spec from monorepo (#246)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-14 07:02:37 -07:00
9312cabf22 chore: update OpenAPI spec from monorepo (#245)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-13 18:10:03 -07:00
ec85ab283b chore: update OpenAPI spec from monorepo (#244)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-13 14:58:31 -07:00
4c5911ffee chore: update OpenAPI spec from monorepo (#243)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-13 13:33:16 -07:00
882f4a0811 chore: update OpenAPI spec from monorepo (#242)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-13 09:29:14 -07:00
90f661ff73 chore: update OpenAPI spec from monorepo (#241)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-13 07:25:17 -07:00
bb74b7fabc chore: update OpenAPI spec from monorepo (#240)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-13 00:43:55 -07:00
a7bb403311 chore: update OpenAPI spec from monorepo (#239)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-12 23:54:21 -07:00
522b03abf3 chore: update OpenAPI spec from monorepo (#238)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-12 21:49:55 -07:00
be479e24fd chore: update OpenAPI spec from monorepo (#237)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-12 18:12:04 -07:00
a4197ac1db chore: update OpenAPI spec from monorepo (#236)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-11 19:37:39 -07:00
f587c3ce45 chore: update OpenAPI spec from monorepo (#235)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-11 16:37:12 -07:00
a4ae8297ce chore: update OpenAPI spec from monorepo (#234)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-09 00:28:51 -07:00
4664c73492 chore: update OpenAPI spec from monorepo (#233)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-08 15:25:45 -07:00
e150991aa7 chore: update OpenAPI spec from monorepo (#232)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-08 07:42:24 -07:00
5f18dd0131 chore: update OpenAPI spec from monorepo (#231)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-07 15:00:54 -07:00
5441e86fee chore: update OpenAPI spec from monorepo (#230)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-06 15:46:15 -07:00
bb505b71e5 chore: update OpenAPI spec from monorepo (#229)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-06 15:03:26 -07:00
45c3ace681 chore: update OpenAPI spec from monorepo (#228)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-06 12:18:59 -07:00
d208cc6cf8 chore: update OpenAPI spec from monorepo (#227)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-06 09:58:16 -07:00
fb31150e8f chore: update OpenAPI spec from monorepo (#226)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-06 03:37:55 -07:00
e0e80c538a chore: update OpenAPI spec from monorepo (#224)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-05 21:16:03 -07:00
7db74e51d1 chore: update OpenAPI spec from monorepo (#223)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-05 18:17:00 -07:00
27c12d4d59 chore: update OpenAPI spec from monorepo (#222)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-05 09:56:31 -07:00
cd24443470 chore: update OpenAPI spec from monorepo (#221)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-05 08:47:57 -07:00
2fc0ea8084 chore: update OpenAPI spec from monorepo (#220)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-04 15:06:32 -05:00
330cff1158 chore: update OpenAPI spec from monorepo (#219)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-04 14:33:14 -05:00
8ac9dede84 chore: update OpenAPI spec from monorepo (#218)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-05-02 12:45:50 -05:00
c10bbfe084 chore: update OpenAPI spec from monorepo (#216)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-30 12:23:07 -05:00
3d1fdef97a chore: update OpenAPI spec from monorepo (#215)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-30 04:07:15 -05:00
067cdc027a chore: update OpenAPI spec from monorepo (#214)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-27 20:53:22 -05:00
5bad276c29 chore: update OpenAPI spec from monorepo (#211)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-24 09:05:21 -05:00
f3699017d5 chore: update OpenAPI spec from monorepo (#193)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-23 10:06:30 -05:00
b202e599ae chore: update OpenAPI spec from monorepo (#190)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-23 00:06:20 -05:00
be9056bcbe chore: update OpenAPI spec from monorepo (#177)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-22 09:03:32 -05:00
cb23cec150 chore: update OpenAPI spec from monorepo (#164)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-21 14:55:33 -05:00
312ffce1c5 chore: update OpenAPI spec from monorepo (#151)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-20 13:33:39 -05:00
c5e87b6ab2 chore: update OpenAPI spec from monorepo (#150)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-20 07:44:12 -05:00
a23c20f60b chore: update OpenAPI spec from monorepo (#146)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-19 10:30:32 -05:00
e6703a5038 chore: update OpenAPI spec from monorepo (#143)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-18 23:28:56 -05:00
9ce403745a chore: update OpenAPI spec from monorepo (#141)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-18 20:28:30 -05:00
175b135377 chore: update OpenAPI spec from monorepo (#135)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-17 19:46:43 -05:00
0503928934 chore: update OpenAPI spec from monorepo (#132)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-16 15:19:12 -05:00
6006c3a84f chore: update OpenAPI spec from monorepo (#131)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-16 12:44:05 -05:00
c2a933ff6b chore: update OpenAPI spec from monorepo (#130)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-16 09:56:09 -05:00
a34a1456a1 chore: update OpenAPI spec from monorepo (#126)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-15 16:04:08 -05:00
a40c0019c1 chore: update OpenAPI spec from monorepo (#125)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-15 09:38:49 -05:00
5881e47375 chore: update OpenAPI spec from monorepo (#124)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-14 15:01:06 -05:00
6989ad4f40 chore: update OpenAPI spec from monorepo (#122)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-14 11:59:16 -05:00
Matt AppersonandGitHub b2386114cd fix: add overlay to remove nullable from pagination offset params (#121) 2026-04-14 12:48:15 -04:00
2bba049182 chore: update OpenAPI spec from monorepo (#119)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-14 09:43:17 -05:00
e8953c70bd chore: update OpenAPI spec from monorepo (#113)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-13 12:55:39 -05:00
29fdfcedc3 chore: update OpenAPI spec from monorepo (#112)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-13 11:15:35 -05:00
c0959955c1 chore: update OpenAPI spec from monorepo (#110)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-13 03:41:31 -05:00
a0a7edecfa chore: update OpenAPI spec from monorepo (#106)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-12 12:21:17 -05:00
4e84bb736b chore: update OpenAPI spec from monorepo (#98)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-10 21:16:40 -04:00
947e92e68d chore: update OpenAPI spec from monorepo (#99)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-10 21:16:13 -04:00
bdbd8becc2 chore: update OpenAPI spec from monorepo (#97)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-10 21:15:46 -04:00
6ef088e7c7 chore: update OpenAPI spec from monorepo (#100)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-10 21:15:45 -04:00
e4e5cc259a chore: update OpenAPI spec from monorepo (#101)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
2026-04-10 21:14:47 -04:00
Matt AppersonandGitHub 06bea2ae0f chore: set forwardCompatibleUnionsByDefault to tagged-only (#76) 2026-04-08 10:46:15 -04:00
Matt AppersonandGitHub 6b1b7e6a9d fix: add overlay to convert boolean query params to boolean type (#75) 2026-04-08 09:22:13 -04:00
Matt AppersonandGitHub dd8e6bdac2 fix: add generic overlay to remove redundant allOf inline enums (#73) 2026-04-03 18:37:50 -04:00
Matt Apperson e6b0242969 chore: clean up removed docs and update generated SDK files
Remove obsolete component documentation and update speakeasy-generated
files to match the latest OpenAPI spec regeneration.
2026-04-02 10:21:41 -04:00
1202 changed files with 124666 additions and 67792 deletions
@@ -0,0 +1,86 @@
name: Auto-merge Speakeasy PR
# Speakeasy mode:pr opens PRs (speakeasy-sdk-regen-*) and labels them
# patch/minor/major. Merge automatically so sdk_publish.yaml can run.
on:
pull_request:
types: [labeled]
permissions:
contents: write
pull-requests: write
concurrency:
group: auto-merge-speakeasy
cancel-in-progress: false
jobs:
auto-merge:
if: |
github.event.sender.login == 'github-actions[bot]' &&
github.event.pull_request.user.login == 'github-actions[bot]' &&
startsWith(github.event.pull_request.head.ref, 'speakeasy-sdk-regen-') &&
contains(github.event.pull_request.title, '🐝 Update SDK') &&
contains(fromJSON('["patch", "minor", "major"]'), github.event.label.name)
runs-on: ubuntu-latest
steps:
- name: Close superseded Speakeasy PRs
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
set -euo pipefail
CURRENT_PR="${{ github.event.pull_request.number }}"
PRIOR_JSON=$(gh pr list \
--repo "${{ github.repository }}" \
--state open \
--search "head:speakeasy-sdk-regen-" \
--limit 500 \
--json number \
| jq -r --arg cur "$CURRENT_PR" \
'[.[].number | select(tostring != $cur)] | .[]')
if [ -z "$PRIOR_JSON" ]; then
echo "No superseded Speakeasy PRs to close"
exit 0
fi
mapfile -t PRIOR <<< "$PRIOR_JSON"
echo "Closing ${#PRIOR[@]} superseded Speakeasy PR(s)"
for N in "${PRIOR[@]}"; do
gh pr close "$N" --repo "${{ github.repository }}" --delete-branch \
--comment "Superseded by newer Speakeasy SDK generation PR #${CURRENT_PR}" \
|| echo "::warning::Failed to close PR #$N (continuing)"
sleep 1
done
- name: Auto-merge Speakeasy PR
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
set -euo pipefail
PR_NUM="${{ github.event.pull_request.number }}"
REPO="${{ github.repository }}"
STATE=$(gh pr view "$PR_NUM" --repo "$REPO" --json state --jq .state)
if [ "$STATE" != "OPEN" ]; then
echo "PR #$PR_NUM is $STATE — skipping merge"
exit 0
fi
# Prefer GitHub auto-merge when required checks exist; otherwise
# squash-merge directly (same pattern as sdk-release-prs.yaml).
AUTO_MERGE_NOOP_PATTERN='is in clean status|protected branch rules|Branch does not have required protected branch rules'
if gh pr merge "$PR_NUM" --repo "$REPO" --squash --auto --delete-branch 2> /tmp/gh-merge.err; then
echo "Auto-merge enabled for Speakeasy PR #$PR_NUM"
elif grep -qiE "$AUTO_MERGE_NOOP_PATTERN" /tmp/gh-merge.err; then
echo "Auto-merge not applicable — merging PR #$PR_NUM directly"
cat /tmp/gh-merge.err >&2
gh pr merge "$PR_NUM" --repo "$REPO" --squash --delete-branch
else
echo "::error::Failed to enable auto-merge on Speakeasy PR #$PR_NUM"
cat /tmp/gh-merge.err >&2
exit 1
fi
@@ -0,0 +1,36 @@
name: Generate (spec change merged)
permissions:
checks: write
contents: write
pull-requests: write
statuses: write
id-token: write
"on":
workflow_dispatch:
inputs:
force:
description: Force generation of SDKs
type: boolean
default: false
set_version:
description: optionally set a specific SDK version
type: string
pull_request:
types: [closed]
branches:
- main
paths:
- .speakeasy/in.openapi.yaml
jobs:
generate:
if: github.event.pull_request.merged == true || github.event_name == 'workflow_dispatch'
uses: speakeasy-api/sdk-generation-action/.github/workflows/workflow-executor.yaml@v15
with:
force: ${{ github.event.inputs.force }}
mode: pr
set_version: ${{ github.event.inputs.set_version }}
secrets:
github_access_token: ${{ secrets.GITHUB_TOKEN }}
pypi_token: ${{ secrets.PYPI_TOKEN }}
speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}
+6831 -2816
View File
File diff suppressed because it is too large Load Diff
+2 -1
View File
@@ -32,7 +32,7 @@ generation:
skipResponseBodyAssertions: false
preApplyUnionDiscriminators: true
python:
version: 0.8.0
version: 0.10.1
additionalDependencies:
dev: {}
main: {}
@@ -59,6 +59,7 @@ python:
flattenGlobalSecurity: true
flattenRequests: true
flatteningOrder: parameters-first
forwardCompatibleUnionsByDefault: tagged-only
imports:
option: openapi
paths:
+31244 -17979
View File
File diff suppressed because it is too large Load Diff
+31762 -18663
View File
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,11 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Simplify redundant allOf inline schemas
version: 0.0.0
actions:
- target: "$..allOf[?@.enum && !@['$ref']]"
description: >
Remove inline enum definitions that duplicate a $ref enum in the same
allOf. These are artifacts from zod-openapi .extend() serialization.
remove: true
@@ -0,0 +1,10 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Convert boolean query params from string to boolean
version: 0.0.0
actions:
- target: $..parameters[?@.schema["x-openrouter-type"] == "boolean"].schema
description: Convert x-openrouter-type boolean params from string to boolean
update:
type: boolean
@@ -0,0 +1,10 @@
overlay: 1.0.0
x-speakeasy-jsonpath: rfc9535
info:
title: Fix nullable pagination params
version: 0.0.0
actions:
- target: $..parameters[?@.name == "offset" && @.in == "query"].schema
description: Remove nullable from offset query params to fix mypy errors in pagination helpers
update:
nullable: false
+9 -11
View File
@@ -1,26 +1,21 @@
speakeasyVersion: 1.680.0
sources:
-OAS:
sourceNamespace: open-router-chat-completions-api
sourceRevisionDigest: sha256:01256c8494de6bfc13c36d82ae316a6a13d402194f844618bcd4d59e34f325f3
sourceBlobDigest: sha256:4c80e48fd5e1cd030e68d664eb93984b4d5946867252ff1755a2bd2a05eccd4e
tags:
- latest
OpenRouter API:
sourceNamespace: open-router-chat-completions-api
sourceRevisionDigest: sha256:c6e52cd6931f7230cd3c226f7482b02dc0dfd682cd14540deb6f721fc0fe9d83
sourceBlobDigest: sha256:01ccba21dd9b8695a4071a9f75c329c4c57fdc2c8dfc0ee189ddb2e5ea1dfecb
sourceRevisionDigest: sha256:3961034f6f0bdec425b86df15fce217a97ac7b47776d8a0c815e3dd64ebd81de
sourceBlobDigest: sha256:4e1f247864fe64f3cd13e9a6d8e3215f118d8497db4d1eb58e5c803d0d34b5dc
tags:
- latest
- speakeasy-sdk-regen-1781825192
- 1.0.0
targets:
open-router:
source: OpenRouter API
sourceNamespace: open-router-chat-completions-api
sourceRevisionDigest: sha256:c6e52cd6931f7230cd3c226f7482b02dc0dfd682cd14540deb6f721fc0fe9d83
sourceBlobDigest: sha256:01ccba21dd9b8695a4071a9f75c329c4c57fdc2c8dfc0ee189ddb2e5ea1dfecb
sourceRevisionDigest: sha256:3961034f6f0bdec425b86df15fce217a97ac7b47776d8a0c815e3dd64ebd81de
sourceBlobDigest: sha256:4e1f247864fe64f3cd13e9a6d8e3215f118d8497db4d1eb58e5c803d0d34b5dc
codeSamplesNamespace: open-router-python-code-samples
codeSamplesRevisionDigest: sha256:1a98221b7ae69cb68277c44cbbaac0c80b5260821b687848445bbc6dddc26894
codeSamplesRevisionDigest: sha256:d59fc8e5b1b99b9889f59b905f8ecf55e91c3ded775b70c80e3c3b3a940f9eba
workflow:
workflowVersion: 1.0.0
speakeasyVersion: 1.680.0
@@ -32,6 +27,9 @@ workflow:
- location: .speakeasy/overlays/open-enums.overlay.yaml
- location: .speakeasy/overlays/remove-rss-responses.overlay.yaml
- location: .speakeasy/overlays/add-headers.overlay.yaml
- location: .speakeasy/overlays/allof-simplify.overlay.yaml
- location: .speakeasy/overlays/boolean-query-params.overlay.yaml
- location: .speakeasy/overlays/fix-nullable-pagination.overlay.yaml
output: .speakeasy/out.openapi.yaml
registry:
location: registry.speakeasyapi.dev/openrouter/sdk/open-router-chat-completions-api
+3
View File
@@ -8,6 +8,9 @@ sources:
- location: .speakeasy/overlays/open-enums.overlay.yaml
- location: .speakeasy/overlays/remove-rss-responses.overlay.yaml
- location: .speakeasy/overlays/add-headers.overlay.yaml
- location: .speakeasy/overlays/allof-simplify.overlay.yaml
- location: .speakeasy/overlays/boolean-query-params.overlay.yaml
- location: .speakeasy/overlays/fix-nullable-pagination.overlay.yaml
output: .speakeasy/out.openapi.yaml
registry:
location: registry.speakeasyapi.dev/openrouter/sdk/open-router-chat-completions-api
+1 -1
View File
@@ -1,6 +1,6 @@
# OpenRouter Python SDK
The OpenRouter Python SDK is a type-safe toolkit for building AI applications with access to 300+ language models through a unified API.
The OpenRouter Python SDK is a type-safe toolkit for building AI applications with access to 400+ language models through a unified API.
## Why use the OpenRouter SDK?
+66 -9
View File
@@ -1,6 +1,6 @@
# OpenRouter SDK (Beta)
# OpenRouter SDK
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to over 300 models across providers in an easy and type-safe way.
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to 400+ models across providers in an easy and type-safe way.
To learn more about how to use the OpenRouter SDK, check out our [API Reference](https://openrouter.ai/docs/sdks/python/reference) and [Documentation](https://openrouter.ai/docs/sdks/python).
@@ -169,6 +169,69 @@ asyncio.run(main())
<!-- No Custom HTTP Client [http-client] -->
<!-- Start Pagination [pagination] -->
## Pagination
Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the
returned response object will have a `Next` method that can be called to pull down the next group of results. If the
return value of `Next` is `None`, then there are no more pages to be fetched.
Here's an example of one such pagination call:
```python
from openrouter import OpenRouter
import os
with OpenRouter(
http_referer="<value>",
x_open_router_title="<value>",
x_open_router_categories="<value>",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.byok.list()
while res is not None:
# Handle items
res = res.next()
```
<!-- End Pagination [pagination] -->
<!-- Start File uploads [file-upload] -->
## File uploads
Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.
> [!TIP]
>
> For endpoints that handle file uploads bytes arrays can also be used. However, using streams is recommended for large files.
>
```python
from openrouter import OpenRouter
import os
with OpenRouter(
http_referer="<value>",
x_open_router_title="<value>",
x_open_router_categories="<value>",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.files.upload(file={
"file_name": "example.file",
"content": open("example.file", "rb"),
})
# Handle response
print(res)
```
<!-- End File uploads [file-upload] -->
<!-- Start Resource Management [resource-management] -->
## Resource Management
@@ -246,10 +309,4 @@ To run the test suite, you'll need to set up your environment with an OpenRouter
```bash
pytest
```
## Maturity
This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
looking for the latest version.
```
+66 -9
View File
@@ -1,6 +1,6 @@
# OpenRouter SDK (Beta)
# OpenRouter SDK
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to over 300 models across providers in an easy and type-safe way.
The [OpenRouter SDK](https://openrouter.ai/docs/sdks/python) is a Python toolkit designed to help you build AI-powered features and solutions. Giving you easy access to 400+ models across providers in an easy and type-safe way.
To learn more about how to use the OpenRouter SDK, check out our [API Reference](https://openrouter.ai/docs/sdks/python/reference) and [Documentation](https://openrouter.ai/docs/sdks/python).
@@ -169,6 +169,69 @@ asyncio.run(main())
<!-- No Custom HTTP Client [http-client] -->
<!-- Start Pagination [pagination] -->
## Pagination
Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the
returned response object will have a `Next` method that can be called to pull down the next group of results. If the
return value of `Next` is `None`, then there are no more pages to be fetched.
Here's an example of one such pagination call:
```python
from openrouter import OpenRouter
import os
with OpenRouter(
http_referer="<value>",
x_open_router_title="<value>",
x_open_router_categories="<value>",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.byok.list()
while res is not None:
# Handle items
res = res.next()
```
<!-- End Pagination [pagination] -->
<!-- Start File uploads [file-upload] -->
## File uploads
Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.
> [!TIP]
>
> For endpoints that handle file uploads bytes arrays can also be used. However, using streams is recommended for large files.
>
```python
from openrouter import OpenRouter
import os
with OpenRouter(
http_referer="<value>",
x_open_router_title="<value>",
x_open_router_categories="<value>",
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.files.upload(file={
"file_name": "example.file",
"content": open("example.file", "rb"),
})
# Handle response
print(res)
```
<!-- End File uploads [file-upload] -->
<!-- Start Resource Management [resource-management] -->
## Resource Management
@@ -246,10 +309,4 @@ To run the test suite, you'll need to set up your environment with an OpenRouter
```bash
pytest
```
## Maturity
This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
looking for the latest version.
```
+31 -1
View File
@@ -8,4 +8,34 @@ Based on:
### Generated
- [python v0.0.16] .
### Releases
- [PyPI v0.0.16] https://pypi.org/project/openrouter/0.0.16 - .
- [PyPI v0.0.16] https://pypi.org/project/openrouter/0.0.16 - .
## 2026-06-11 00:55:55
### Changes
Based on:
- OpenAPI Doc
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
### Generated
- [python v0.9.2] .
### Releases
- [PyPI v0.9.2] https://pypi.org/project/openrouter/0.9.2 - .
## 2026-06-17 00:59:07
### Changes
Based on:
- OpenAPI Doc
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
### Generated
- [python v0.10.0] .
### Releases
- [PyPI v0.10.0] https://pypi.org/project/openrouter/0.10.0 - .
## 2026-06-19 01:04:04
### Changes
Based on:
- OpenAPI Doc
- Speakeasy CLI 1.680.0 (2.788.4) https://github.com/speakeasy-api/speakeasy
### Generated
- [python v0.10.1] .
### Releases
- [PyPI v0.10.1] https://pypi.org/project/openrouter/0.10.1 - .
+6 -10
View File
@@ -12,12 +12,10 @@ with OpenRouter(
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = open_router.beta.responses.send(service_tier="auto", stream=False)
res = open_router.analytics.get_user_activity()
with res as event_stream:
for event in event_stream:
# handle event
print(event, flush=True)
# Handle response
print(res)
```
</br>
@@ -39,12 +37,10 @@ async def main():
api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:
res = await open_router.beta.responses.send_async(service_tier="auto", stream=False)
res = await open_router.analytics.get_user_activity_async()
async with res as event_stream:
async for event in event_stream:
# handle event
print(event, flush=True)
# Handle response
print(res)
asyncio.run(main())
```
+7 -7
View File
@@ -5,14 +5,14 @@
| Field | Type | Required | Description | Example |
| --------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------- |
| `byok_usage_inference` | *float* | :heavy_check_mark: | BYOK inference cost in USD (external credits spent) | 0.012 |
| `completion_tokens` | *int* | :heavy_check_mark: | Total completion tokens generated | 125 |
| `date_` | *str* | :heavy_check_mark: | Date of the activity (YYYY-MM-DD format) | 2025-08-24 |
| `endpoint_id` | *str* | :heavy_check_mark: | Unique identifier for the endpoint | 550e8400-e29b-41d4-a716-446655440000 |
| `model` | *str* | :heavy_check_mark: | Model slug (e.g., "openai/gpt-4.1") | openai/gpt-4.1 |
| `model_permaslug` | *str* | :heavy_check_mark: | Model permaslug (e.g., "openai/gpt-4.1-2025-04-14") | openai/gpt-4.1-2025-04-14 |
| `endpoint_id` | *str* | :heavy_check_mark: | Unique identifier for the endpoint | 550e8400-e29b-41d4-a716-446655440000 |
| `prompt_tokens` | *int* | :heavy_check_mark: | Total prompt tokens used | 50 |
| `provider_name` | *str* | :heavy_check_mark: | Name of the provider serving this endpoint | OpenAI |
| `usage` | *float* | :heavy_check_mark: | Total cost in USD (OpenRouter credits spent) | 0.015 |
| `byok_usage_inference` | *float* | :heavy_check_mark: | BYOK inference cost in USD (external credits spent) | 0.012 |
| `requests` | *float* | :heavy_check_mark: | Number of requests made | 5 |
| `prompt_tokens` | *float* | :heavy_check_mark: | Total prompt tokens used | 50 |
| `completion_tokens` | *float* | :heavy_check_mark: | Total completion tokens generated | 125 |
| `reasoning_tokens` | *float* | :heavy_check_mark: | Total reasoning tokens used | 25 |
| `reasoning_tokens` | *int* | :heavy_check_mark: | Total reasoning tokens used | 25 |
| `requests` | *int* | :heavy_check_mark: | Number of requests made | 5 |
| `usage` | *float* | :heavy_check_mark: | Total cost in USD (OpenRouter credits spent) | 0.015 |
+4 -4
View File
@@ -7,8 +7,8 @@ Model architecture information
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------------ | ------------------------------------------------------------------ |
| `tokenizer` | [Nullable[components.Tokenizer]](../components/tokenizer.md) | :heavy_check_mark: | N/A | GPT |
| `instruct_type` | [Nullable[components.InstructType]](../components/instructtype.md) | :heavy_check_mark: | Instruction format type | |
| `modality` | *Nullable[str]* | :heavy_check_mark: | Primary modality of the model | text |
| `input_modalities` | List[[components.InputModality](../components/inputmodality.md)] | :heavy_check_mark: | Supported input modalities | |
| `output_modalities` | List[[components.OutputModality](../components/outputmodality.md)] | :heavy_check_mark: | Supported output modalities | |
| `instruct_type` | [Nullable[components.InstructType]](../components/instructtype.md) | :heavy_check_mark: | Instruction format type | chatml |
| `modality` | *Nullable[str]* | :heavy_check_mark: | Primary modality of the model | text |
| `output_modalities` | List[[components.OutputModality](../components/outputmodality.md)] | :heavy_check_mark: | Supported output modalities | |
| `tokenizer` | [Nullable[components.Tokenizer]](../components/tokenizer.md) | :heavy_check_mark: | N/A | GPT |
-17
View File
@@ -1,17 +0,0 @@
# AssistantMessage
Assistant message for requests and responses
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
| `role` | [components.AssistantMessageRole](../components/assistantmessagerole.md) | :heavy_check_mark: | N/A | |
| `content` | [OptionalNullable[components.AssistantMessageContent]](../components/assistantmessagecontent.md) | :heavy_minus_sign: | Assistant message content | |
| `name` | *Optional[str]* | :heavy_minus_sign: | Optional name for the assistant | |
| `tool_calls` | List[[components.ChatMessageToolCall](../components/chatmessagetoolcall.md)] | :heavy_minus_sign: | Tool calls made by the assistant | |
| `refusal` | *OptionalNullable[str]* | :heavy_minus_sign: | Refusal message if content was refused | |
| `reasoning` | *OptionalNullable[str]* | :heavy_minus_sign: | Reasoning output | |
| `reasoning_details` | List[[components.ReasoningDetailUnion](../components/reasoningdetailunion.md)] | :heavy_minus_sign: | Reasoning details for extended thinking models | |
| `images` | List[[components.AssistantMessageImages](../components/assistantmessageimages.md)] | :heavy_minus_sign: | Generated images from image generation models | [<br/>{<br/>"image_url": {<br/>"url": "data:image/png;base64,iVBORw0KGgo..."<br/>}<br/>}<br/>] |
@@ -1,25 +0,0 @@
# AssistantMessageContent
Assistant message content
## Supported Types
### `str`
```python
value: str = /* values here */
```
### `List[components.ChatMessageContentItem]`
```python
value: List[components.ChatMessageContentItem] = /* values here */
```
### `Any`
```python
value: Any = /* values here */
```
@@ -1,8 +0,0 @@
# AssistantMessageImages
## Fields
| Field | Type | Required | Description |
| -------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- |
| `image_url` | [components.AssistantMessageImagesImageURL](../components/assistantmessageimagesimageurl.md) | :heavy_check_mark: | N/A |
@@ -1,8 +0,0 @@
# AssistantMessageImagesImageURL
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------- | ------------------------------------------------- | ------------------------------------------------- | ------------------------------------------------- |
| `url` | *str* | :heavy_check_mark: | URL or base64-encoded data of the generated image |
-8
View File
@@ -1,8 +0,0 @@
# AssistantMessageRole
## Values
| Name | Value |
| ----------- | ----------- |
| `ASSISTANT` | assistant |
-10
View File
@@ -1,10 +0,0 @@
# ChainID
## Values
| Name | Value |
| --------------------------------------------- | --------------------------------------------- |
| `ONE` | 1 |
| `ONE_HUNDRED_AND_THIRTY_SEVEN` | 137 |
| `EIGHT_THOUSAND_FOUR_HUNDRED_AND_FIFTY_THREE` | 8453 |
@@ -1,12 +0,0 @@
# ChatCompletionFinishReason
## Values
| Name | Value |
| ---------------- | ---------------- |
| `TOOL_CALLS` | tool_calls |
| `STOP` | stop |
| `LENGTH` | length |
| `CONTENT_FILTER` | content_filter |
| `ERROR` | error |
-39
View File
@@ -1,39 +0,0 @@
# ChatGenerationParams
Chat completion request parameters
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `provider` | [OptionalNullable[components.ChatGenerationParamsProvider]](../components/chatgenerationparamsprovider.md) | :heavy_minus_sign: | When multiple model providers are available, optionally indicate your routing preference. | |
| `plugins` | List[[components.ChatGenerationParamsPluginUnion](../components/chatgenerationparamspluginunion.md)] | :heavy_minus_sign: | Plugins you want to enable for this request, including their settings. | |
| `user` | *Optional[str]* | :heavy_minus_sign: | Unique user identifier | user-123 |
| `session_id` | *Optional[str]* | :heavy_minus_sign: | A unique identifier for grouping related requests (e.g., a conversation or agent workflow) for observability. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 128 characters. | |
| `trace` | [Optional[components.ChatGenerationParamsTrace]](../components/chatgenerationparamstrace.md) | :heavy_minus_sign: | Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations. | |
| `messages` | List[[components.Message](../components/message.md)] | :heavy_check_mark: | List of messages for the conversation | [<br/>{<br/>"role": "user",<br/>"content": "Hello!"<br/>}<br/>] |
| `model` | *Optional[str]* | :heavy_minus_sign: | Model to use for completion | openai/gpt-4 |
| `models` | List[*str*] | :heavy_minus_sign: | Models to use for completion | [<br/>"openai/gpt-4",<br/>"openai/gpt-4o"<br/>] |
| `frequency_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | Frequency penalty (-2.0 to 2.0) | 0 |
| `logit_bias` | Dict[str, *float*] | :heavy_minus_sign: | Token logit bias adjustments | {<br/>"50256": -100<br/>} |
| `logprobs` | *OptionalNullable[bool]* | :heavy_minus_sign: | Return log probabilities | false |
| `top_logprobs` | *OptionalNullable[float]* | :heavy_minus_sign: | Number of top log probabilities to return (0-20) | 5 |
| `max_completion_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum tokens in completion | 100 |
| `max_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Maximum tokens (deprecated, use max_completion_tokens) | 100 |
| `metadata` | Dict[str, *str*] | :heavy_minus_sign: | Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values) | {<br/>"user_id": "user-123",<br/>"session_id": "session-456"<br/>} |
| `presence_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | Presence penalty (-2.0 to 2.0) | 0 |
| `reasoning` | [Optional[components.Reasoning]](../components/reasoning.md) | :heavy_minus_sign: | Configuration options for reasoning models | {<br/>"effort": "medium",<br/>"summary": "concise"<br/>} |
| `response_format` | [Optional[components.ResponseFormat]](../components/responseformat.md) | :heavy_minus_sign: | Response format configuration | {<br/>"type": "json_object"<br/>} |
| `seed` | *OptionalNullable[int]* | :heavy_minus_sign: | Random seed for deterministic outputs | 42 |
| `stop` | [OptionalNullable[components.Stop]](../components/stop.md) | :heavy_minus_sign: | Stop sequences (up to 4) | [<br/>""<br/>] |
| `stream` | *Optional[bool]* | :heavy_minus_sign: | Enable streaming response | false |
| `stream_options` | [OptionalNullable[components.ChatStreamOptions]](../components/chatstreamoptions.md) | :heavy_minus_sign: | Streaming configuration options | {<br/>"include_usage": true<br/>} |
| `temperature` | *OptionalNullable[float]* | :heavy_minus_sign: | Sampling temperature (0-2) | 0.7 |
| `parallel_tool_calls` | *OptionalNullable[bool]* | :heavy_minus_sign: | N/A | |
| `tool_choice` | [Optional[components.ToolChoiceOption]](../components/toolchoiceoption.md) | :heavy_minus_sign: | Tool choice configuration | auto |
| `tools` | List[[components.ToolDefinitionJSON](../components/tooldefinitionjson.md)] | :heavy_minus_sign: | Available tools for function calling | [<br/>{<br/>"type": "function",<br/>"function": {<br/>"name": "get_weather",<br/>"description": "Get weather"<br/>}<br/>}<br/>] |
| `top_p` | *OptionalNullable[float]* | :heavy_minus_sign: | Nucleus sampling parameter (0-1) | 1 |
| `debug` | [Optional[components.DebugOptions]](../components/debugoptions.md) | :heavy_minus_sign: | Debug options for inspecting request transformations (streaming only) | {<br/>"echo_upstream_body": true<br/>} |
| `image_config` | Dict[str, [components.ChatGenerationParamsImageConfig](../components/chatgenerationparamsimageconfig.md)] | :heavy_minus_sign: | Provider-specific image configuration options. Keys and values vary by model/provider. See https://openrouter.ai/docs/guides/overview/multimodal/image-generation for more details. | {<br/>"aspect_ratio": "16:9"<br/>} |
| `modalities` | List[[components.Modality](../components/modality.md)] | :heavy_minus_sign: | Output modalities for the response. Supported values are "text" and "image". | [<br/>"text",<br/>"image"<br/>] |
-12
View File
@@ -1,12 +0,0 @@
# ChatGenerationParamsBy
The provider sorting strategy (price, throughput, latency)
## Values
| Name | Value |
| ------------ | ------------ |
| `PRICE` | price |
| `THROUGHPUT` | throughput |
| `LATENCY` | latency |
@@ -1,9 +0,0 @@
# ChatGenerationParamsEngine
## Values
| Name | Value |
| -------- | -------- |
| `NATIVE` | native |
| `EXA` | exa |
@@ -1,8 +0,0 @@
# ChatGenerationParamsIDAutoRouter
## Values
| Name | Value |
| ------------- | ------------- |
| `AUTO_ROUTER` | auto-router |
@@ -1,8 +0,0 @@
# ChatGenerationParamsIDFileParser
## Values
| Name | Value |
| ------------- | ------------- |
| `FILE_PARSER` | file-parser |
@@ -1,8 +0,0 @@
# ChatGenerationParamsIDModeration
## Values
| Name | Value |
| ------------ | ------------ |
| `MODERATION` | moderation |
@@ -1,8 +0,0 @@
# ChatGenerationParamsIDResponseHealing
## Values
| Name | Value |
| ------------------ | ------------------ |
| `RESPONSE_HEALING` | response-healing |
@@ -1,8 +0,0 @@
# ChatGenerationParamsIDWeb
## Values
| Name | Value |
| ----- | ----- |
| `WEB` | web |
@@ -1,17 +0,0 @@
# ChatGenerationParamsIgnore
## Supported Types
### `components.ProviderName`
```python
value: components.ProviderName = /* values here */
```
### `str`
```python
value: str = /* values here */
```
@@ -1,23 +0,0 @@
# ChatGenerationParamsImageConfig
## Supported Types
### `str`
```python
value: str = /* values here */
```
### `float`
```python
value: float = /* values here */
```
### `List[Nullable[Any]]`
```python
value: List[Nullable[Any]] = /* values here */
```
@@ -1,14 +0,0 @@
# ChatGenerationParamsMaxPrice
The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion.
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------- | ------------------------------- | ------------------------------- | ------------------------------- | ------------------------------- |
| `prompt` | *Optional[str]* | :heavy_minus_sign: | Price per million prompt tokens | 1000 |
| `completion` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
| `image` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
| `audio` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
| `request` | *Optional[str]* | :heavy_minus_sign: | N/A | 1000 |
@@ -1,17 +0,0 @@
# ChatGenerationParamsOnly
## Supported Types
### `components.ProviderName`
```python
value: components.ProviderName = /* values here */
```
### `str`
```python
value: str = /* values here */
```
@@ -1,17 +0,0 @@
# ChatGenerationParamsOrder
## Supported Types
### `components.ProviderName`
```python
value: components.ProviderName = /* values here */
```
### `str`
```python
value: str = /* values here */
```
@@ -1,11 +0,0 @@
# ChatGenerationParamsPartition
Partitioning strategy for sorting: "model" (default) groups endpoints by model before sorting (fallback models remain fallbacks), "none" sorts all endpoints together regardless of model.
## Values
| Name | Value |
| ------- | ------- |
| `MODEL` | model |
| `NONE` | none |
@@ -1,8 +0,0 @@
# ChatGenerationParamsPdf
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
| `engine` | [Optional[components.ChatGenerationParamsPdfEngine]](../components/chatgenerationparamspdfengine.md) | :heavy_minus_sign: | N/A |
@@ -1,10 +0,0 @@
# ChatGenerationParamsPdfEngine
## Values
| Name | Value |
| ------------- | ------------- |
| `MISTRAL_OCR` | mistral-ocr |
| `PDF_TEXT` | pdf-text |
| `NATIVE` | native |
@@ -1,10 +0,0 @@
# ChatGenerationParamsPluginAutoRouter
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | [components.ChatGenerationParamsIDAutoRouter](../components/chatgenerationparamsidautorouter.md) | :heavy_check_mark: | N/A | |
| `enabled` | *Optional[bool]* | :heavy_minus_sign: | Set to false to disable the auto-router plugin for this request. Defaults to true. | |
| `allowed_models` | List[*str*] | :heavy_minus_sign: | List of model patterns to filter which models the auto-router can route between. Supports wildcards (e.g., "anthropic/*" matches all Anthropic models). When not specified, uses the default supported models list. | [<br/>"anthropic/*",<br/>"openai/gpt-4o",<br/>"google/*"<br/>] |
@@ -1,10 +0,0 @@
# ChatGenerationParamsPluginFileParser
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
| `id` | [components.ChatGenerationParamsIDFileParser](../components/chatgenerationparamsidfileparser.md) | :heavy_check_mark: | N/A |
| `enabled` | *Optional[bool]* | :heavy_minus_sign: | Set to false to disable the file-parser plugin for this request. Defaults to true. |
| `pdf` | [Optional[components.PDFParserOptions]](../components/pdfparseroptions.md) | :heavy_minus_sign: | Options for PDF parsing. |
@@ -1,8 +0,0 @@
# ChatGenerationParamsPluginModeration
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
| `id` | [components.ChatGenerationParamsIDModeration](../components/chatgenerationparamsidmoderation.md) | :heavy_check_mark: | N/A |
@@ -1,9 +0,0 @@
# ChatGenerationParamsPluginResponseHealing
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| `id` | [components.ChatGenerationParamsIDResponseHealing](../components/chatgenerationparamsidresponsehealing.md) | :heavy_check_mark: | N/A |
| `enabled` | *Optional[bool]* | :heavy_minus_sign: | Set to false to disable the response-healing plugin for this request. Defaults to true. |
@@ -1,35 +0,0 @@
# ChatGenerationParamsPluginUnion
## Supported Types
### `components.ChatGenerationParamsPluginAutoRouter`
```python
value: components.ChatGenerationParamsPluginAutoRouter = /* values here */
```
### `components.ChatGenerationParamsPluginModeration`
```python
value: components.ChatGenerationParamsPluginModeration = /* values here */
```
### `components.ChatGenerationParamsPluginWeb`
```python
value: components.ChatGenerationParamsPluginWeb = /* values here */
```
### `components.ChatGenerationParamsPluginFileParser`
```python
value: components.ChatGenerationParamsPluginFileParser = /* values here */
```
### `components.ChatGenerationParamsPluginResponseHealing`
```python
value: components.ChatGenerationParamsPluginResponseHealing = /* values here */
```
@@ -1,12 +0,0 @@
# ChatGenerationParamsPluginWeb
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------- |
| `id` | [components.ChatGenerationParamsIDWeb](../components/chatgenerationparamsidweb.md) | :heavy_check_mark: | N/A |
| `enabled` | *Optional[bool]* | :heavy_minus_sign: | Set to false to disable the web-search plugin for this request. Defaults to true. |
| `max_results` | *Optional[float]* | :heavy_minus_sign: | N/A |
| `search_prompt` | *Optional[str]* | :heavy_minus_sign: | N/A |
| `engine` | [Optional[components.WebSearchEngine]](../components/websearchengine.md) | :heavy_minus_sign: | The search engine to use for web search. |
@@ -1,22 +0,0 @@
# ChatGenerationParamsProvider
When multiple model providers are available, optionally indicate your routing preference.
## Fields
| Field | Type | Required | Description | Example |
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `allow_fallbacks` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to allow backup providers to serve requests<br/>- true: (default) when the primary provider (or your custom providers in "order") is unavailable, use the next best provider.<br/>- false: use only the primary/custom provider, and return the upstream error if it's unavailable.<br/> | |
| `require_parameters` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to filter providers to only those that support the parameters you've provided. If this setting is omitted or set to false, then providers will receive only the parameters they support, and ignore the rest. | |
| `data_collection` | [OptionalNullable[components.DataCollection]](../components/datacollection.md) | :heavy_minus_sign: | Data collection setting. If no available model provider meets the requirement, your request will return an error.<br/>- allow: (default) allow providers which store user data non-transiently and may train on it<br/><br/>- deny: use only providers which do not collect user data. | allow |
| `zdr` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to restrict routing to only ZDR (Zero Data Retention) endpoints. When true, only endpoints that do not retain prompts will be used. | true |
| `enforce_distillable_text` | *OptionalNullable[bool]* | :heavy_minus_sign: | Whether to restrict routing to only models that allow text distillation. When true, only models where the author has allowed distillation will be used. | true |
| `order` | List[[components.ChatGenerationParamsOrder](../components/chatgenerationparamsorder.md)] | :heavy_minus_sign: | An ordered list of provider slugs. The router will attempt to use the first provider in the subset of this list that supports your requested model, and fall back to the next if it is unavailable. If no providers are available, the request will fail with an error message. | |
| `only` | List[[components.ChatGenerationParamsOnly](../components/chatgenerationparamsonly.md)] | :heavy_minus_sign: | List of provider slugs to allow. If provided, this list is merged with your account-wide allowed provider settings for this request. | |
| `ignore` | List[[components.ChatGenerationParamsIgnore](../components/chatgenerationparamsignore.md)] | :heavy_minus_sign: | List of provider slugs to ignore. If provided, this list is merged with your account-wide ignored provider settings for this request. | |
| `quantizations` | List[[components.Quantization](../components/quantization.md)] | :heavy_minus_sign: | A list of quantization levels to filter the provider by. | |
| `sort` | [OptionalNullable[components.ChatGenerationParamsSortUnion]](../components/chatgenerationparamssortunion.md) | :heavy_minus_sign: | N/A | price |
| `max_price` | [Optional[components.ChatGenerationParamsMaxPrice]](../components/chatgenerationparamsmaxprice.md) | :heavy_minus_sign: | The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion. | |
| `preferred_min_throughput` | [OptionalNullable[components.PreferredMinThroughput]](../components/preferredminthroughput.md) | :heavy_minus_sign: | Preferred minimum throughput (in tokens per second). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints below the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold. | 100 |
| `preferred_max_latency` | [OptionalNullable[components.PreferredMaxLatency]](../components/preferredmaxlatency.md) | :heavy_minus_sign: | Preferred maximum latency (in seconds). Can be a number (applies to p50) or an object with percentile-specific cutoffs. Endpoints above the threshold(s) may still be used, but are deprioritized in routing. When using fallback models, this may cause a fallback model to be used instead of the primary model if it meets the threshold. | 5 |
@@ -1,12 +0,0 @@
# ChatGenerationParamsProviderSort
The provider sorting strategy (price, throughput, latency)
## Values
| Name | Value |
| ------------ | ------------ |
| `PRICE` | price |
| `THROUGHPUT` | throughput |
| `LATENCY` | latency |
@@ -1,9 +0,0 @@
# ChatGenerationParamsProviderSortConfig
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `by` | [OptionalNullable[components.ChatGenerationParamsBy]](../components/chatgenerationparamsby.md) | :heavy_minus_sign: | The provider sorting strategy (price, throughput, latency) | price |
| `partition` | [OptionalNullable[components.ChatGenerationParamsPartition]](../components/chatgenerationparamspartition.md) | :heavy_minus_sign: | Partitioning strategy for sorting: "model" (default) groups endpoints by model before sorting (fallback models remain fallbacks), "none" sorts all endpoints together regardless of model. | model |
@@ -1,10 +0,0 @@
# ChatGenerationParamsProviderSortConfigEnum
## Values
| Name | Value |
| ------------ | ------------ |
| `PRICE` | price |
| `THROUGHPUT` | throughput |
| `LATENCY` | latency |
@@ -1,17 +0,0 @@
# ChatGenerationParamsProviderSortConfigUnion
## Supported Types
### `components.ChatGenerationParamsProviderSortConfig`
```python
value: components.ChatGenerationParamsProviderSortConfig = /* values here */
```
### `components.ChatGenerationParamsProviderSortConfigEnum`
```python
value: components.ChatGenerationParamsProviderSortConfigEnum = /* values here */
```
@@ -1,9 +0,0 @@
# ChatGenerationParamsRoute
## Values
| Name | Value |
| ---------- | ---------- |
| `FALLBACK` | fallback |
| `SORT` | sort |
@@ -1,10 +0,0 @@
# ChatGenerationParamsSortEnum
## Values
| Name | Value |
| ------------ | ------------ |
| `PRICE` | price |
| `THROUGHPUT` | throughput |
| `LATENCY` | latency |
@@ -1,25 +0,0 @@
# ChatGenerationParamsSortUnion
The sorting strategy to use for this request, if "order" is not specified. When set, no load balancing is performed.
## Supported Types
### `components.ChatGenerationParamsProviderSort`
```python
value: components.ChatGenerationParamsProviderSort = /* values here */
```
### `components.ChatGenerationParamsProviderSortConfigUnion`
```python
value: components.ChatGenerationParamsProviderSortConfigUnion = /* values here */
```
### `components.ChatGenerationParamsSortEnum`
```python
value: components.ChatGenerationParamsSortEnum = /* values here */
```
@@ -1,15 +0,0 @@
# ChatGenerationParamsTrace
Metadata for observability and tracing. Known keys (trace_id, trace_name, span_name, generation_name, parent_span_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations.
## Fields
| Field | Type | Required | Description |
| -------------------------- | -------------------------- | -------------------------- | -------------------------- |
| `trace_id` | *Optional[str]* | :heavy_minus_sign: | N/A |
| `trace_name` | *Optional[str]* | :heavy_minus_sign: | N/A |
| `span_name` | *Optional[str]* | :heavy_minus_sign: | N/A |
| `generation_name` | *Optional[str]* | :heavy_minus_sign: | N/A |
| `parent_span_id` | *Optional[str]* | :heavy_minus_sign: | N/A |
| `__pydantic_extra__` | Dict[str, *Nullable[Any]*] | :heavy_minus_sign: | N/A |
@@ -1,14 +0,0 @@
# ChatGenerationTokenUsage
Token usage statistics
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
| `completion_tokens` | *float* | :heavy_check_mark: | Number of tokens in the completion |
| `prompt_tokens` | *float* | :heavy_check_mark: | Number of tokens in the prompt |
| `total_tokens` | *float* | :heavy_check_mark: | Total number of tokens |
| `completion_tokens_details` | [OptionalNullable[components.CompletionTokensDetails]](../components/completiontokensdetails.md) | :heavy_minus_sign: | Detailed completion token usage |
| `prompt_tokens_details` | [OptionalNullable[components.PromptTokensDetails]](../components/prompttokensdetails.md) | :heavy_minus_sign: | Detailed prompt token usage |
-31
View File
@@ -1,31 +0,0 @@
# ChatMessageContentItem
Content part for chat completion messages
## Supported Types
### `components.ChatMessageContentItemText`
```python
value: components.ChatMessageContentItemText = /* values here */
```
### `components.ChatMessageContentItemImage`
```python
value: components.ChatMessageContentItemImage = /* values here */
```
### `components.ChatMessageContentItemAudio`
```python
value: components.ChatMessageContentItemAudio = /* values here */
```
### `components.ChatMessageContentItem1`
```python
value: components.ChatMessageContentItem1 = /* values here */
```
@@ -1,17 +0,0 @@
# ChatMessageContentItem1
## Supported Types
### `components.ChatMessageContentItemVideoLegacy`
```python
value: components.ChatMessageContentItemVideoLegacy = /* values here */
```
### `components.ChatMessageContentItemVideo`
```python
value: components.ChatMessageContentItemVideo = /* values here */
```
@@ -1,11 +0,0 @@
# ChatMessageContentItemAudio
Audio input content part. Supported audio formats vary by provider.
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| `type` | [components.ChatMessageContentItemAudioType](../components/chatmessagecontentitemaudiotype.md) | :heavy_check_mark: | N/A |
| `input_audio` | [components.ChatMessageContentItemAudioInputAudio](../components/chatmessagecontentitemaudioinputaudio.md) | :heavy_check_mark: | N/A |
@@ -1,9 +0,0 @@
# ChatMessageContentItemAudioInputAudio
## Fields
| Field | Type | Required | Description |
| ----------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| `data` | *str* | :heavy_check_mark: | Base64 encoded audio data |
| `format_` | *str* | :heavy_check_mark: | Audio format (e.g., wav, mp3, flac, m4a, ogg, aiff, aac, pcm16, pcm24). Supported formats vary by provider. |
@@ -1,8 +0,0 @@
# ChatMessageContentItemAudioType
## Values
| Name | Value |
| ------------- | ------------- |
| `INPUT_AUDIO` | input_audio |
@@ -1,11 +0,0 @@
# ChatMessageContentItemCacheControl
Cache control for the content part
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ |
| `type` | [components.ChatMessageContentItemCacheControlType](../components/chatmessagecontentitemcachecontroltype.md) | :heavy_check_mark: | N/A |
| `ttl` | [Optional[components.TTL]](../components/ttl.md) | :heavy_minus_sign: | N/A |
@@ -1,8 +0,0 @@
# ChatMessageContentItemCacheControlType
## Values
| Name | Value |
| ----------- | ----------- |
| `EPHEMERAL` | ephemeral |
@@ -1,11 +0,0 @@
# ChatMessageContentItemImage
Image content part for vision models
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------ |
| `type` | [components.ChatMessageContentItemImageType](../components/chatmessagecontentitemimagetype.md) | :heavy_check_mark: | N/A |
| `image_url` | [components.ChatMessageContentItemImageImageURL](../components/chatmessagecontentitemimageimageurl.md) | :heavy_check_mark: | N/A |
@@ -1,12 +0,0 @@
# ChatMessageContentItemImageDetail
Image detail level for vision models
## Values
| Name | Value |
| ------ | ------ |
| `AUTO` | auto |
| `LOW` | low |
| `HIGH` | high |
@@ -1,9 +0,0 @@
# ChatMessageContentItemImageImageURL
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------ |
| `url` | *str* | :heavy_check_mark: | URL of the image (data: URLs supported) |
| `detail` | [Optional[components.ChatMessageContentItemImageDetail]](../components/chatmessagecontentitemimagedetail.md) | :heavy_minus_sign: | Image detail level for vision models |
@@ -1,8 +0,0 @@
# ChatMessageContentItemImageType
## Values
| Name | Value |
| ----------- | ----------- |
| `IMAGE_URL` | image_url |
@@ -1,12 +0,0 @@
# ChatMessageContentItemText
Text content part
## Fields
| Field | Type | Required | Description | Example |
| -------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
| `type` | [components.ChatMessageContentItemTextType](../components/chatmessagecontentitemtexttype.md) | :heavy_check_mark: | N/A | |
| `text` | *str* | :heavy_check_mark: | N/A | |
| `cache_control` | [Optional[components.ChatMessageContentItemCacheControl]](../components/chatmessagecontentitemcachecontrol.md) | :heavy_minus_sign: | Cache control for the content part | {<br/>"type": "ephemeral",<br/>"ttl": "5m"<br/>} |
@@ -1,8 +0,0 @@
# ChatMessageContentItemTextType
## Values
| Name | Value |
| ------ | ------ |
| `TEXT` | text |
@@ -1,11 +0,0 @@
# ChatMessageContentItemVideo
Video input content part
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
| `type` | [components.ChatMessageContentItemVideoType](../components/chatmessagecontentitemvideotype.md) | :heavy_check_mark: | N/A |
| `video_url` | [components.VideoInput](../components/videoinput.md) | :heavy_check_mark: | Video input object |
@@ -1,13 +0,0 @@
# ~~ChatMessageContentItemVideoLegacy~~
Video input content part (legacy format - deprecated)
> :warning: **DEPRECATED**: This will be removed in a future release, please migrate away from it as soon as possible.
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| `type` | [components.ChatMessageContentItemVideoLegacyType](../components/chatmessagecontentitemvideolegacytype.md) | :heavy_check_mark: | N/A |
| `video_url` | [components.VideoInput](../components/videoinput.md) | :heavy_check_mark: | Video input object |
@@ -1,8 +0,0 @@
# ChatMessageContentItemVideoLegacyType
## Values
| Name | Value |
| ------------- | ------------- |
| `INPUT_VIDEO` | input_video |
@@ -1,8 +0,0 @@
# ChatMessageContentItemVideoType
## Values
| Name | Value |
| ----------- | ----------- |
| `VIDEO_URL` | video_url |
@@ -1,13 +0,0 @@
# ChatMessageTokenLogprob
Token log probability information
## Fields
| Field | Type | Required | Description |
| -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- |
| `token` | *str* | :heavy_check_mark: | The token |
| `logprob` | *float* | :heavy_check_mark: | Log probability of the token |
| `bytes_` | List[*float*] | :heavy_check_mark: | UTF-8 bytes of the token |
| `top_logprobs` | List[[components.ChatMessageTokenLogprobTopLogprob](../components/chatmessagetokenlogprobtoplogprob.md)] | :heavy_check_mark: | Top alternative tokens with probabilities |
@@ -1,11 +0,0 @@
# ChatMessageTokenLogprobs
Log probabilities for the completion
## Fields
| Field | Type | Required | Description |
| ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------ |
| `content` | List[[components.ChatMessageTokenLogprob](../components/chatmessagetokenlogprob.md)] | :heavy_check_mark: | Log probabilities for content tokens |
| `refusal` | List[[components.ChatMessageTokenLogprob](../components/chatmessagetokenlogprob.md)] | :heavy_check_mark: | Log probabilities for refusal tokens |
@@ -1,10 +0,0 @@
# ChatMessageTokenLogprobTopLogprob
## Fields
| Field | Type | Required | Description |
| ------------------ | ------------------ | ------------------ | ------------------ |
| `token` | *str* | :heavy_check_mark: | N/A |
| `logprob` | *float* | :heavy_check_mark: | N/A |
| `bytes_` | List[*float*] | :heavy_check_mark: | N/A |
-12
View File
@@ -1,12 +0,0 @@
# ChatMessageToolCall
Tool call made by the assistant
## Fields
| Field | Type | Required | Description |
| -------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
| `id` | *str* | :heavy_check_mark: | Tool call identifier |
| `type` | [components.ChatMessageToolCallType](../components/chatmessagetoolcalltype.md) | :heavy_check_mark: | N/A |
| `function` | [components.ChatMessageToolCallFunction](../components/chatmessagetoolcallfunction.md) | :heavy_check_mark: | N/A |
@@ -1,9 +0,0 @@
# ChatMessageToolCallFunction
## Fields
| Field | Type | Required | Description |
| --------------------------------- | --------------------------------- | --------------------------------- | --------------------------------- |
| `name` | *str* | :heavy_check_mark: | Function name to call |
| `arguments` | *str* | :heavy_check_mark: | Function arguments as JSON string |
@@ -1,8 +0,0 @@
# ChatMessageToolCallType
## Values
| Name | Value |
| ---------- | ---------- |
| `FUNCTION` | function |
-16
View File
@@ -1,16 +0,0 @@
# ChatResponse
Chat completion response
## Fields
| Field | Type | Required | Description | Example |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | *str* | :heavy_check_mark: | Unique completion identifier | chatcmpl-123 |
| `choices` | List[[components.ChatResponseChoice](../components/chatresponsechoice.md)] | :heavy_check_mark: | List of completion choices | |
| `created` | *float* | :heavy_check_mark: | Unix timestamp of creation | 1677652288 |
| `model` | *str* | :heavy_check_mark: | Model used for completion | openai/gpt-4 |
| `object` | [components.ChatResponseObject](../components/chatresponseobject.md) | :heavy_check_mark: | N/A | |
| `system_fingerprint` | *OptionalNullable[str]* | :heavy_minus_sign: | System fingerprint | fp_44709d6fcb |
| `usage` | [Optional[components.ChatGenerationTokenUsage]](../components/chatgenerationtokenusage.md) | :heavy_minus_sign: | Token usage statistics | {<br/>"completion_tokens": 15,<br/>"prompt_tokens": 10,<br/>"total_tokens": 25,<br/>"completion_tokens_details": {<br/>"reasoning_tokens": 5<br/>},<br/>"prompt_tokens_details": {<br/>"cached_tokens": 2<br/>}<br/>} |
-13
View File
@@ -1,13 +0,0 @@
# ChatResponseChoice
Chat completion choice
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ |
| `finish_reason` | *Nullable[Any]* | :heavy_check_mark: | N/A | |
| `index` | *float* | :heavy_check_mark: | Choice index | 0 |
| `message` | [components.AssistantMessage](../components/assistantmessage.md) | :heavy_check_mark: | Assistant message for requests and responses | {<br/>"role": "user",<br/>"content": "What is the capital of France?"<br/>} |
| `logprobs` | [OptionalNullable[components.ChatMessageTokenLogprobs]](../components/chatmessagetokenlogprobs.md) | :heavy_minus_sign: | Log probabilities for the completion | {<br/>"content": [<br/>{<br/>"token": " Hello",<br/>"logprob": -0.612345,<br/>"bytes": null,<br/>"top_logprobs": []<br/>}<br/>],<br/>"refusal": null<br/>} |
-8
View File
@@ -1,8 +0,0 @@
# ChatResponseObject
## Values
| Name | Value |
| ----------------- | ----------------- |
| `CHAT_COMPLETION` | chat.completion |
-13
View File
@@ -1,13 +0,0 @@
# ChatStreamingChoice
Streaming completion choice chunk
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ |
| `delta` | [components.ChatStreamingMessageChunk](../components/chatstreamingmessagechunk.md) | :heavy_check_mark: | Delta changes in streaming response | {<br/>"role": "assistant",<br/>"content": "Hello"<br/>} |
| `finish_reason` | *Nullable[Any]* | :heavy_check_mark: | N/A | |
| `index` | *float* | :heavy_check_mark: | Choice index | 0 |
| `logprobs` | [OptionalNullable[components.ChatMessageTokenLogprobs]](../components/chatmessagetokenlogprobs.md) | :heavy_minus_sign: | Log probabilities for the completion | {<br/>"content": [<br/>{<br/>"token": " Hello",<br/>"logprob": -0.612345,<br/>"bytes": null,<br/>"top_logprobs": []<br/>}<br/>],<br/>"refusal": null<br/>} |
@@ -1,15 +0,0 @@
# ChatStreamingMessageChunk
Delta changes in streaming response
## Fields
| Field | Type | Required | Description | Example |
| ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
| `role` | [Optional[components.ChatStreamingMessageChunkRole]](../components/chatstreamingmessagechunkrole.md) | :heavy_minus_sign: | The role of the message author | assistant |
| `content` | *OptionalNullable[str]* | :heavy_minus_sign: | Message content delta | Hello |
| `reasoning` | *OptionalNullable[str]* | :heavy_minus_sign: | Reasoning content delta | I need to |
| `refusal` | *OptionalNullable[str]* | :heavy_minus_sign: | Refusal message delta | <nil> |
| `tool_calls` | List[[components.ChatStreamingMessageToolCall](../components/chatstreamingmessagetoolcall.md)] | :heavy_minus_sign: | Tool calls delta | |
| `reasoning_details` | List[[components.ReasoningDetailUnion](../components/reasoningdetailunion.md)] | :heavy_minus_sign: | Reasoning details for extended thinking models | |
@@ -1,10 +0,0 @@
# ChatStreamingMessageChunkRole
The role of the message author
## Values
| Name | Value |
| ----------- | ----------- |
| `ASSISTANT` | assistant |
@@ -1,13 +0,0 @@
# ChatStreamingMessageToolCall
Tool call delta for streaming responses
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ |
| `index` | *float* | :heavy_check_mark: | Tool call index in the array | 0 |
| `id` | *Optional[str]* | :heavy_minus_sign: | Tool call identifier | call_abc123 |
| `type` | [Optional[components.ChatStreamingMessageToolCallType]](../components/chatstreamingmessagetoolcalltype.md) | :heavy_minus_sign: | Tool call type | function |
| `function` | [Optional[components.ChatStreamingMessageToolCallFunction]](../components/chatstreamingmessagetoolcallfunction.md) | :heavy_minus_sign: | Function call details | |
@@ -1,11 +0,0 @@
# ChatStreamingMessageToolCallFunction
Function call details
## Fields
| Field | Type | Required | Description | Example |
| --------------------------------- | --------------------------------- | --------------------------------- | --------------------------------- | --------------------------------- |
| `name` | *Optional[str]* | :heavy_minus_sign: | Function name | get_weather |
| `arguments` | *Optional[str]* | :heavy_minus_sign: | Function arguments as JSON string | {"location": |
@@ -1,10 +0,0 @@
# ChatStreamingMessageToolCallType
Tool call type
## Values
| Name | Value |
| ---------- | ---------- |
| `FUNCTION` | function |
@@ -1,17 +0,0 @@
# ChatStreamingResponseChunk
Streaming chat completion chunk
## Fields
| Field | Type | Required | Description | Example |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | *str* | :heavy_check_mark: | Unique chunk identifier | chatcmpl-123 |
| `choices` | List[[components.ChatStreamingChoice](../components/chatstreamingchoice.md)] | :heavy_check_mark: | List of streaming chunk choices | |
| `created` | *float* | :heavy_check_mark: | Unix timestamp of creation | 1677652288 |
| `model` | *str* | :heavy_check_mark: | Model used for completion | openai/gpt-4 |
| `object` | [components.ChatStreamingResponseChunkObject](../components/chatstreamingresponsechunkobject.md) | :heavy_check_mark: | N/A | |
| `system_fingerprint` | *OptionalNullable[str]* | :heavy_minus_sign: | System fingerprint | fp_44709d6fcb |
| `error` | [Optional[components.Error]](../components/error.md) | :heavy_minus_sign: | Error information | {<br/>"message": "Rate limit exceeded",<br/>"code": 429<br/>} |
| `usage` | [Optional[components.ChatGenerationTokenUsage]](../components/chatgenerationtokenusage.md) | :heavy_minus_sign: | Token usage statistics | {<br/>"completion_tokens": 15,<br/>"prompt_tokens": 10,<br/>"total_tokens": 25,<br/>"completion_tokens_details": {<br/>"reasoning_tokens": 5<br/>},<br/>"prompt_tokens_details": {<br/>"cached_tokens": 2<br/>}<br/>} |
@@ -1,8 +0,0 @@
# ChatStreamingResponseChunkObject
## Values
| Name | Value |
| ----------------------- | ----------------------- |
| `CHAT_COMPLETION_CHUNK` | chat.completion.chunk |
+4 -4
View File
@@ -7,7 +7,7 @@ Detailed completion token usage
| Field | Type | Required | Description |
| ---------------------------- | ---------------------------- | ---------------------------- | ---------------------------- |
| `reasoning_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Tokens used for reasoning |
| `audio_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Tokens used for audio output |
| `accepted_prediction_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Accepted prediction tokens |
| `rejected_prediction_tokens` | *OptionalNullable[float]* | :heavy_minus_sign: | Rejected prediction tokens |
| `accepted_prediction_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Accepted prediction tokens |
| `audio_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Tokens used for audio output |
| `reasoning_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Tokens used for reasoning |
| `rejected_prediction_tokens` | *OptionalNullable[int]* | :heavy_minus_sign: | Rejected prediction tokens |
+7 -5
View File
@@ -1,10 +1,12 @@
# CostDetails
Breakdown of upstream inference costs
## Fields
| Field | Type | Required | Description |
| -------------------------------- | -------------------------------- | -------------------------------- | -------------------------------- |
| `upstream_inference_cost` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `upstream_inference_input_cost` | *float* | :heavy_check_mark: | N/A |
| `upstream_inference_output_cost` | *float* | :heavy_check_mark: | N/A |
| Field | Type | Required | Description |
| ------------------------------------- | ------------------------------------- | ------------------------------------- | ------------------------------------- |
| `upstream_inference_completions_cost` | *float* | :heavy_check_mark: | N/A |
| `upstream_inference_cost` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `upstream_inference_prompt_cost` | *float* | :heavy_check_mark: | N/A |
-12
View File
@@ -1,12 +0,0 @@
# CreateChargeRequest
Create a Coinbase charge for crypto payment
## Fields
| Field | Type | Required | Description |
| ---------------------------------------------- | ---------------------------------------------- | ---------------------------------------------- | ---------------------------------------------- |
| `amount` | *float* | :heavy_check_mark: | N/A |
| `sender` | *str* | :heavy_check_mark: | N/A |
| `chain_id` | [components.ChainID](../components/chainid.md) | :heavy_check_mark: | N/A |
-10
View File
@@ -1,10 +0,0 @@
# Data
Model count data
## Fields
| Field | Type | Required | Description | Example |
| -------------------------------- | -------------------------------- | -------------------------------- | -------------------------------- | -------------------------------- |
| `count` | *float* | :heavy_check_mark: | Total number of available models | 150 |
-10
View File
@@ -1,10 +0,0 @@
# DebugOptions
Debug options for inspecting request transformations (streaming only)
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------ |
| `echo_upstream_body` | *Optional[bool]* | :heavy_minus_sign: | If true, includes the transformed upstream request body in a debug chunk at the start of the stream. Only works with streaming mode. | true |
+4 -4
View File
@@ -7,9 +7,9 @@ Default parameters for this model
| Field | Type | Required | Description |
| ------------------------- | ------------------------- | ------------------------- | ------------------------- |
| `temperature` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `top_p` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `top_k` | *OptionalNullable[int]* | :heavy_minus_sign: | N/A |
| `frequency_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `presence_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `repetition_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `repetition_penalty` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `temperature` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
| `top_k` | *OptionalNullable[int]* | :heavy_minus_sign: | N/A |
| `top_p` | *OptionalNullable[float]* | :heavy_minus_sign: | N/A |
-12
View File
@@ -1,12 +0,0 @@
# DeveloperMessage
Developer message
## Fields
| Field | Type | Required | Description | Example |
| ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ |
| `role` | [components.DeveloperMessageRole](../components/developermessagerole.md) | :heavy_check_mark: | N/A | |
| `content` | [components.DeveloperMessageContent](../components/developermessagecontent.md) | :heavy_check_mark: | Developer message content | This is a message from the developer. |
| `name` | *Optional[str]* | :heavy_minus_sign: | Optional name for the developer message | Developer |
@@ -1,19 +0,0 @@
# DeveloperMessageContent
Developer message content
## Supported Types
### `str`
```python
value: str = /* values here */
```
### `List[components.ChatMessageContentItemText]`
```python
value: List[components.ChatMessageContentItemText] = /* values here */
```
-8
View File
@@ -1,8 +0,0 @@
# DeveloperMessageRole
## Values
| Name | Value |
| ----------- | ----------- |
| `DEVELOPER` | developer |

Some files were not shown because too many files have changed in this diff Show More