bbaf0af907
Grayswan guardrail passthrough on flagged ( #16891 )
...
* attempt to implement the passthrough feature
* Formatting and small change
* Fix formatting
* Format test file
---------
Co-authored-by: Xiaohan Fu <xiaohan@grayswan.ai >
2025-11-21 20:01:35 -08:00
db58f6aeb1
fix: arize phoenix logging ( #16301 )
...
* arize phx
* fix arize integration
* traces to specific project name
* fix
* look for http endpoint
2025-11-21 18:46:18 -08:00
1ebe1fea37
Docs for Model Compare UI and Org Usage ( #16928 )
...
* Docs for Model Compare UI and Org Usage
* Fix typo in img path and add Model Compare to sidebars.js
* Updated to remove from 1.80 writeup
2025-11-21 16:45:55 -08:00
8e318dd06c
[Feat] New LLM Provider - Docker Model Runner ( #16948 )
...
* add DOCKER_MODEL_RUNNER
* add DockerModelRunnerChatConfig Transorm
* add docker_model_runner
* add docker_model_runner
* docs docker model runner
* add DockerModelRunnerChatConfig
* add docker_model_runner to providers
* test_completion_hits_correct_url_and_body
* fix sidebar
* TestDockerModelRunnerIntegration
* test_completion_with_custom_engine_and_host
* docs docker model runner
* docs fix
2025-11-21 16:09:32 -08:00
5b4a848391
fix anthropic pass-through endpoint ( #16883 )
2025-11-21 16:00:05 -08:00
1c65800f4a
Feat: add support for Grok 4.1 Fast models ( #16936 )
...
* feat: Add support for Grok 4.1 Fast models
Add new xAI Grok 4.1 Fast models optimized for high-performance agentic tool calling:
- xai/grok-4-1-fast (alias for grok-4-1-fast-reasoning)
- xai/grok-4-1-fast-reasoning (with reasoning capabilities)
- xai/grok-4-1-fast-reasoning-latest
- xai/grok-4-1-fast-non-reasoning (without reasoning for faster responses)
- xai/grok-4-1-fast-non-reasoning-latest
Features:
- Context window: 2,000,000 tokens
- Pricing: $0.20/1M input, $0.50/1M output tokens
- Cached tokens: $0.05/1M tokens
- Supports: Function calling, Structured outputs, Vision, Audio input, Web search, Reasoning
Fixes #16927
* docs: Add comprehensive Grok models documentation
- Add 'Supported Models' section highlighting new Grok 4.1 Fast models
- Include comparison guide for reasoning vs non-reasoning models
- Add complete model family table (Grok 4.1, 4, 3, Code, 2)
- Add features legend explaining capabilities
- Remove pricing details (link to xAI docs instead for current rates)
- Improve documentation clarity and consistency
Related to #16927
* docs: Minor corrections to xai.md
2025-11-21 15:57:55 -08:00
7c4ef090c1
docs: fix mcp url format ( #16940 )
...
* docs: fix mcp url format
* fix: update Cursor MCP example to use url instead of server_url
2025-11-21 15:43:26 -08:00
f9d8eeaf8e
[stripe] gemini 3 thought signatures in tool call id ( #16895 )
...
* though signature tool call id
* [stripe] refactor and tests
* [stripe] remove md and move to factory
* [stripe] remove redudant test
* [stripe] ran black formatting
* [stripe] add thought signature docs
* [stripe] remove unused import
2025-11-21 13:44:53 -08:00
041ac054b6
feat: allow custom violation message for tool-permission guardrail ( #16916 )
2025-11-21 08:52:01 -08:00
e7751f0c12
docs: fix docs bug
2025-11-20 16:05:39 -08:00
57544f1662
[Feat] Adds IAM role assumption support for AWS Secret Manager ( #16887 )
...
* add AWS fields for KeyManagementSettings
* docs IAM roles
* use aws iam auth on secret manager v2
* fix: load_aws_secret_manager
* test_secret_manager_with_iam_role_settings
2025-11-20 12:38:48 -08:00
9120a02474
Change favicon ( #16837 )
2025-11-19 20:38:22 -08:00
28cadaa123
docs: fix tags
2025-11-19 20:26:48 -08:00
0389f2d064
docs: cleanup
2025-11-19 20:26:48 -08:00
87be419559
docs(index.md): cleanup
2025-11-19 20:23:22 -08:00
778425f02f
docs: add initial blog post for Gemini 3 on LiteLLM
2025-11-19 20:22:24 -08:00
208027dc71
docs(ui.md): reorder ui page
2025-11-19 19:17:54 -08:00
6fc7397dde
Add Vertex AI Image Edit Support ( #16828 )
...
* Add vertex ai image edit support
* Fix lint errors
2025-11-19 18:39:28 -08:00
08246bf908
fix: fix broken doc link
2025-11-19 08:35:38 -08:00
afc9a763cb
Fix IBM Guardrails optional params, add extra_headers field ( #16771 )
...
Signed-off-by: Rob Geada <rob@geada.net >
2025-11-18 19:55:40 -08:00
35ab0e109c
[Docs] SSO - Manage User Roles via Azure App Roles ( #16796 )
...
* add img 2
* add app roles
* docs
2025-11-18 16:00:36 -08:00
f9ec353b80
[Feature] UI - Allow setting base_url in API reference docs ( #16674 )
...
* Allow setting base_url in API reference docs
* Add logic to change base url for test key page
2025-11-18 11:27:28 -08:00
acf206bec6
Add Day 0 gemini-3-pro-preview support ( #16719 )
...
* Add thinking signature support for gemini
* Add docs related to thinking signature
* remove double base64 import
* fix mypy errors
* fix litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py mypy
* Add new gemini 3 model and features
* Add docs related to gemini 3
* Update gemini 3 pricing
* fix llm translation tests
* fix mapped tests
2025-11-18 09:44:45 -08:00
4dbbec233c
Snowflake provider support: added embeddings, PAT, account_id ( #15727 )
...
* added oauth mcp to docs
* added azure ai/grok-4 model family
* Revert "added oauth mcp to docs"
This reverts commit 950b7cef44f14b2db1429f6fbd32548a7c95d325.
* fix: arize ui integration
* need to remove a file
This reverts commit d6c877b73ac763464f204b77135f3786342373b7.
* snowflake support PAT, account_id and embeddings
* format
* test embeddings
* format
* complete test
* fix: add arize from ui
* updated clarifai functions to openai compatible (#15615 )
* fix: npm build errors
* update tests
* SnowflakeBaseConfig moved to utils
* rename pat_key => api_ke
* key_type=PAT => 'pat/key'
* fix if api_key is None
* doc update
* doc update
---------
Co-authored-by: mubashir1osmani <mubashir.osmani777@gmail.com >
Co-authored-by: Mubashir Osmani <ilikewafflesomcuh@gmail.com >
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com >
Co-authored-by: mogith-pn <143642606+mogith-pn@users.noreply.github.com >
2025-11-17 20:27:46 -08:00
070db16f87
this yaml actually works ( #16757 )
2025-11-17 20:09:44 -08:00
d93e13be36
OCI Provider - Add oci_endpoint_id Parameter for OCI Dedicated Endpoints #16723
2025-11-17 19:59:34 -08:00
88b71863ae
docs(openai): Add gpt-5.1-codex and gpt-5.1-codex-mini models to documentation ( #16735 )
...
- Add gpt-5.1, gpt-5.1-codex, and gpt-5.1-codex-mini to OpenAI Chat Completion Models table
- Add gpt-5.1-codex and gpt-5.1-codex-mini to reasoning_effort supported models table
- Clarify that GPT-5-Codex models (gpt-5-codex, gpt-5.1-codex, gpt-5.1-codex-mini) do NOT support verbosity parameter
- Update verbosity section to exclude Codex variants from supported models list
Note: Model configurations already exist in model_prices_and_context_window.json
2025-11-17 19:50:58 -08:00
bdb1e16dcf
[Feat] AI Gateway Auth - Allow using JWTs for signing in with Proxy CLI ( #16756 )
...
* fix auth
* get_cli_jwt_auth_token
* fix linting
* test fixes
* docs
* test fixes
* fix refactor
2025-11-17 19:47:29 -08:00
5ae99e2761
docs: respect system color scheme preference in Docusaurus ( #16748 )
...
Configure Docusaurus to automatically detect and respect the user's
system/browser color scheme preference (prefers-color-scheme).
This improves UX by matching the documentation theme to the user's
OS-level dark/light mode setting, while still allowing manual override
via the theme switcher.
Changes:
- Add colorMode configuration to docusaurus.config.js
- Enable respectPrefersColorScheme option
2025-11-17 19:46:56 -08:00
f2314bab34
docs: improve dev docs
2025-11-17 19:46:39 -08:00
b9bc903536
remove deprecated embedding model ( #16724 )
2025-11-17 18:46:20 -08:00
7cebc151b0
Add managed files support for responses API ( #16733 )
...
* Fix responses api with managed files
* fix litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py mypy
* fix litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py mypy
* fix mypy errors
2025-11-17 18:41:26 -08:00
83ea037bc9
[Feat] AI Gateway - Allow admins to disable, dynamic callback controls ( #16750 )
...
* add flag to allow_dynamic_callback_disabling
* fix EnterpriseCallbackControls
* test controls
* add docs on dynamic logging
2025-11-17 18:29:07 -08:00
fdb5df1f27
docs(managed_batches.md): update docs
2025-11-17 18:00:08 -08:00
e73ac28178
docs(ui_logs.md): link to spec showing what gets logged
2025-11-17 17:56:24 -08:00
1cdd4065a6
docs: fix docs
2025-11-17 17:54:26 -08:00
6444bf366c
[Docs] mcp oauth flow details ( #16742 )
...
* docs: mcp oauth flow details
* fix: Exception (AsyncHTTPHandler.__init__() got an unexpected keyword argument 'follow_redirects')
2025-11-17 17:45:03 -08:00
08e115ecff
[Feat] Add SSML Support for Azure Text-to-Speech (AVA) ( #16747 )
...
* detect SSML in input
* transform_text_to_speech_request
* test_litellm_speech_with_ssml_passthrough
* add Passing Raw SSML
* fix is_ssml_input
2025-11-17 15:41:22 -08:00
88f5110e11
docs: improve docs
2025-11-17 09:54:13 -08:00
3c6f81e6ce
docs: simplify docs
2025-11-17 09:39:32 -08:00
0292b84dc4
docs: add missing details to benchmark comparison ( #16690 )
2025-11-15 20:12:32 -08:00
b79e92a21b
docs(index.md): document new agent hub
2025-11-15 18:49:51 -08:00
39917f2ff7
Agents - AI Hub, make agents discoverable on model hub page for internal discovery ( #16678 )
...
* feat: initial commit adding agent hub to ui
* feat: add viewable agent hub
* feat: working support for making both config + db agents public via new 'public_agent_groups' list
* fix: agents.py
fix types
* feat: working PATCH endpoint for UI changes
* feat: add new agents panel with working crud
* refactor: refactor to show created_at on be/fe
* style: align new page with the agents table
* style: more style alignment logic
* feat: return if agent is public or not in /v1/agents
* feat: initial commit adding ui flow for making agents discoverable
* feat: new batch make public endpoint
* feat(public_model_hub.tsx): show public agents on public model hub table page
* fix(public_model_hub.tsx): add code examples for using the agent in a2a
* fix: fix indicating if agent has already been made public
* docs: document expected spec for agents is A2A
* docs: add agent hub docs
* docs: document making agents discoverable
* docs: add demo video to docs
* fix: fix ui linting errors
* fix: update tests
2025-11-15 18:25:16 -08:00
6b9fbc5a36
fix docs
2025-11-15 16:58:47 -08:00
f9b5820ba8
fix build
2025-11-15 16:53:12 -08:00
25cb873467
[UI] expose backend endpoint for callbacks settings ( #16698 )
...
* init json for
* add SQS fields
* fix params
* return callbacks configs
* test_get_callback_configs
* test_get_callback_configs
* vercel build fix
2025-11-15 16:44:17 -08:00
60691b771c
add perf update to release notes ( #16697 )
2025-11-15 16:36:49 -08:00
c7807f4841
fix pkg
2025-11-15 16:26:56 -08:00
d9fd7138f9
docs fix
2025-11-15 16:17:04 -08:00
2a006cabac
docs fix
2025-11-15 16:11:31 -08:00
Derek Duenas