What's Changed
- [Feat] Expose Responses API on LiteLLM UI Test Key Page by @ishaan-jaff in #10166
- [Bug Fix] Spend Tracking Bug Fix, don't modify in memory default litellm params by @ishaan-jaff in #10167
- Bug Fix - Responses API, Loosen restrictions on allowed environments for computer use tool by @ishaan-jaff in #10168
- [UI] Bug Fix, team model selector by @ishaan-jaff in #10171
- [Bug Fix] Auth Check, Fix typing to ensure case where model is None is handled by @ishaan-jaff in #10170
- [Docs] Responses API by @ishaan-jaff in #10172
- Litellm release notes 04 19 2025 by @krrishdholakia in #10169
- fix(transformation.py): pass back in gemini thinking content to api by @krrishdholakia in #10173
- Litellm docs SCIM by @ishaan-jaff in #10174
- fix(common_daily_activity.py): support empty entity id field by @krrishdholakia in #10175
- fix(proxy_server.py): pass llm router to get complete model list by @krrishdholakia in #10176
- Model pricing updates for Azure & VertexAI by @marty-sullivan in #10178
- fix(bedrock): wrong system prompt transformation by @hewliyang in #10120
- Fix: Potential SQLi in spend_management_endpoints.py by @n1lanjan in #9878
- Handle edge case where user sets model_group inside model_info + Return hashed_token in
tokenfield on/key/generateby @krrishdholakia in #10191 - Remove user_id from url by @krrishdholakia in #10192
- [Feat] Pass through endpoints - ensure
PassthroughStandardLoggingPayloadis logged and contains method, url, request/response body by @ishaan-jaff in #10194 - [Feat] Add Responses API - Routing Affinity logic for sessions by @ishaan-jaff in #10193
- [Feat] Add infinity embedding support (contributor pr) by @ishaan-jaff in #10196
- [Bug Fix] caching does not account for thinking or reasoning_effort config by @ishaan-jaff in #10140
- Gemini-2.5-flash improvements by @krrishdholakia in #10198
- Add AgentOps Integration to LiteLLM by @Dwij1704 in #9685
- Add global filtering to Users tab by @krrishdholakia in #10195
- [Feat] Add Support for DELETE /v1/responses/{response_id} on OpenAI, Azure OpenAI by @ishaan-jaff in #10205
- Bug Fix - Address deprecation of open_text by @ishaan-jaff in #10208
- UI - Users page - Enable global sorting (allows finding users with highest spend) by @krrishdholakia in #10211
- feat: Added Missing Attributes For Arize & Phoenix Integration (#10043) by @ishaan-jaff in #10215
- Users page - new user info pane by @krrishdholakia in #10213
- Fix datadog llm observability logging + (Responses API) Ensures handling for undocumented event types by @krrishdholakia in #10206
- Discard duplicate sentence by @DimitriPapadopoulos in #10231
- Require auth for all dashboard pages by @crisshaker in #10229
- [Feat] Add gpt-image-1 cost tracking by @ishaan-jaff in #10241
- [Bug Fix] Add Cost Tracking for gpt-image-1 when quality is unspecified by @ishaan-jaff in #10247
- [Feat] Add support for GET Responses Endpoint - OpenAI, Azure OpenAI by @ishaan-jaff in #10235
- fix(user_dashboard.tsx): add token expiry logic to user dashboard by @krrishdholakia in #10250
- [Helm] fix for serviceAccountName on migration job by @ishaan-jaff in #10258
- Fix typos by @DimitriPapadopoulos in #10232
- Reset key alias value when resetting filters by @crisshaker in #10099
- Support all compatible bedrock params when model="arn:.." by @krrishdholakia in #10256
- UI - fix edit azure public model name + support changing model names post create by @krrishdholakia in #10249
- Litellm fix UI login by @krrishdholakia in #10260
- Multi-admin + Users page fixes: show all models, show user personal models, allow editing user role, available models by @krrishdholakia in #10259
- Fix UI Flicker in Dashboard by @crisshaker in #10261
- Keys and tools pages: Use proper terminology for loading and no data cases by @msabramo in #10253
- adding support for cohere command-a-03-2025 by @ryanchase-cohere in #10295
- [Feat] Add GET, DELETE Responses endpoints on LiteLLM Proxy by @ishaan-jaff in #10297
- [Bug Fix] Timestamp Granularities are not properly passed to whisper in Azure by @ishaan-jaff in #10299
- Contributor PR - Support max_completion_tokens on Sagemaker (#10243) by @ishaan-jaff in #10300
- feat(grafana_dashboard): enable datasource selection via templating by @minatoaquaMK2 in #10257
- Update image_generation.md parameters by @daureg in #10312
- Update deprecation dates and prices by @o-khytrov in #10308
- Fix SSO user login - invalid token error by @krrishdholakia in #10298
- UI - Add team based filtering to models page by @krrishdholakia in #10325
- UI (Teams Page) - Support filtering by team id + team name by @krrishdholakia in #10324
- Move UI to encrypted token usage by @krrishdholakia in #10302
- add azure/gpt-image-1 pricing by @marty-sullivan in #10327
- fix(ui_sso.py): support experimental jwt keys for UI auth w/ SSO by @krrishdholakia in #10326
- UI (Keys Page) - Support cross filtering, filter by user id, filter by key hash by @krrishdholakia in #10322
- [Feat] Responses API - Add session management support for non-openai models by @ishaan-jaff in #10321
- Fix the table render on key creation. by @NANDINI-star in #10224
- Internal Users: Refresh user list on create by @crisshaker in #10296
- [Docs] UI Session Logs by @ishaan-jaff in #10334
New Contributors
- @Dwij1704 made their first contribution in #9685
- @DimitriPapadopoulos made their first contribution in #10231
- @ryanchase-cohere made their first contribution in #10295
- @minatoaquaMK2 made their first contribution in #10257
- @daureg made their first contribution in #10312
- @o-khytrov made their first contribution in #10308
Full Changelog: v1.67.0-stable...v1.67.4-stable