491f57a349
feat: Add support for reasoning_effort="none" for Gemini models ( #16548 )
...
Implements support for reasoning_effort="none" parameter for Gemini models,
providing significant cost savings (up to 96% cheaper) by disabling thinking
budget while maintaining response quality.
Changes:
- Added "supports_reasoning": true to gemini-2.0-flash-thinking-exp-01-21 in model config
- Implemented mapping for reasoning_effort="none" to thinkingConfig {thinkingBudget: 0, includeThoughts: false}
- Added unit test to verify the mapping works correctly
Performance impact:
- Without reasoning_effort: ~313 tokens
- With reasoning_effort="none": ~12 tokens (96% cheaper)
Closes #16420
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com >
2025-11-12 19:41:07 -08:00
c017f665e0
docs(openai): Document reasoning_effort summary field options ( #16549 )
...
Related to PR #16210 which fixed automatic summary field addition
Changes:
- Document reasoning_effort string vs dict formats
- Add summary field options (auto, detailed, concise)
- Add table of supported reasoning_effort values by GPT-5 model
- Clarify model-specific support and limitations
- Note that summary field requires org verification
The previous implementation automatically added summary field causing
400 errors for unverified orgs. Now users can opt-in by passing
reasoning_effort as dict with explicit summary field.
2025-11-12 19:40:11 -08:00
018bd2e039
Add Gemini image edit support ( #16430 )
...
* Add gemini image edit support
* fix lint errors
* fix lint errors
* fix lint errors
* Add docs
2025-11-12 18:48:27 -08:00
78c169a524
docs fix
2025-11-12 18:30:01 -08:00
394da34a0b
Add all gemini image models support in image generation ( #16526 )
2025-11-12 18:26:44 -08:00
b30439257b
[Feat] Add RunwayML Img Gen API support ( #16557 )
...
* TestRunwaymlImageGeneration
* fix RUNWAYML
* rename
* fix rename
* get_runwayml_image_generation_config
* get_runwayml_image_generation_config
* TestRunwaymlImageGeneration
* add RUNWAYML_POLLING_TIMEOUT
* fix rnwayml transform img gen
* runwayml_image_cost_calculator
* runwayml_image_cost_calculator
* docs runwayml
* fix runwayML polling
* test_get_first_default_fallback
2025-11-12 18:20:14 -08:00
1393900c22
[Docs] Fix code block indentation for fallbacks page ( #16542 )
2025-11-12 18:08:52 -08:00
a05ad46394
feat: add litellm cloud self-serve to docs
2025-11-12 17:13:14 -08:00
ae3178d5d4
docs(deploy.md): document how to disable pulling live model prices (faster startup time) on docker deployment
2025-11-12 13:49:44 -08:00
020a66c01f
docs(model_access_guide.md): explain how model access works on litellm
2025-11-12 13:44:38 -08:00
c6d2714c52
docs(model_access_guide.md): document how model access works on litellm
2025-11-12 13:43:13 -08:00
20350fa094
docs: update broken Slack invite links to support page ( #16546 )
...
Replace broken Slack links (litellmossslack.slack.com and expired invite URLs)
with the correct support page URL (https://www.litellm.ai/support ) across all
documentation files.
Files updated:
- CONTRIBUTING.md
- docs/my-website/docs/contact.md
- docs/my-website/docs/proxy/docker_quick_start.md
- docs/my-website/docs/troubleshoot.md
- docs/my-website/src/pages/contact.md
2025-11-12 12:41:55 -08:00
a1748ad550
Documentation Code Example corrections ( #16502 )
...
* Update quick_start.md
changed -D to -d
* Update users.md
Changed in a number of locations:
"budget_duration": 10s,
to
"budget_duration": "10s",
* Update users.md
Changed all 10s to 30s to keep in line with the example
2025-11-11 19:06:44 -08:00
50b5cf5215
[Feat] New Provider - Add RunwayML Provider for video generations ( #16505 )
...
* add RUNWAYML
* init folders
* add RunwayMLVideoConfig
* add RUNWAYML_DEFAULT_API_VERSION
* add RunwayMLVideoConfig
* fix getting status
* add async_transform_video_content_response
* add runwayml transform_video_content_response
* fix config.yaml
* add runwayml docs
* add runwayml to videos
* docs runwayml video gen
* add new models to model cost map
* TestRunwayMLVideoTransformation
* fix linting errors
2025-11-11 18:48:23 -08:00
663f2d7e7f
docs: remove enterprise restriction from guardrails list endpoint ( #15333 )
...
- Remove enterprise-only label from 'View Available Guardrails' section
- The /guardrails/list endpoint appears to be available in OSS version
- Makes documentation more accurate for OSS users
2025-11-11 18:45:26 -08:00
443bada425
Add Zscaler AI Guard hook ( #15691 )
...
* Add Zscaler AI Guard hook
Co-authored-by: Angela Tao <atao@zscaler.com >
* Fix lint error, update document
* Fix lint error, update document
* update document
* fix mypy type error
* fix mypy issue
* fix test
* fix test
* improve document
* remove unuseful code
* use litellm httphandler
* update test cases
* revover guardrail_initializers.py and guardrail_registry.py
* remove unuse import
* app apply_guardrail
* remove functions repleased by apply_guardrail, update test and doc
* remove functions repleased by apply_guardrail, update test and doc
---------
Co-authored-by: Angela Tao <atao@zscaler.com >
2025-11-11 15:34:27 -08:00
be05324645
docs fix MAX_LANGFUSE_INITIALIZED_CLIENTS
2025-11-11 11:26:33 -08:00
5c9f50d584
[AI Gateway] - End User Budgets - Allow pointing max_end_user budget to an id, so the default ID applies to all end users ( #16456 )
...
* add _apply_budget_limits_to_end_user_params
* add _apply_budget_limits_to_end_user_params
* add _apply_budget_limits_to_end_user_params
* test_default_budget_applied_to_end_user_without_budget
* docs fix
* fix config
2025-11-11 08:20:13 -08:00
aaa8cba00b
Add docs for tracking callback failure ( #16474 )
2025-11-10 19:15:14 -08:00
bf363cdf10
Add sdk focused examples ( #16441 )
2025-11-10 18:39:34 -08:00
be3c09e6d5
Add GET list of providers endpoint ( #16432 )
2025-11-10 18:38:09 -08:00
a97676b8ae
Add softgen to projects that are using litellm ( #16423 )
...
* Add Softgen project documentation
* Add Softgen project to sidebars
* Update Softgen
2025-11-10 11:09:29 -08:00
013c195ab7
Fix container api link ( #16440 )
2025-11-10 11:09:10 -08:00
50f35fca47
docs: reorder docs
2025-11-10 07:33:22 -08:00
c088483da9
docs playground
2025-11-08 18:15:52 -08:00
f2832ba2f8
docs fix
2025-11-08 17:25:01 -08:00
b803af4aae
docs fix
2025-11-08 17:05:20 -08:00
36d181e398
docs fix + linting fix
2025-11-08 17:02:00 -08:00
42c1e4740a
docs built in guard
2025-11-08 16:59:00 -08:00
a298a9d492
docs fix
2025-11-08 16:52:26 -08:00
7fb46e0b29
docs fix
2025-11-08 16:50:51 -08:00
4647b41d7f
docs fix
2025-11-08 16:50:06 -08:00
08cfc2bf7e
[Docs] Litellm 1 79 2 rc ( #16415 )
...
* stash - v1
* docs fix
* docs fix
* docs
* folder fix
* docs fix
2025-11-08 16:47:15 -08:00
277b564385
add: performance improvements to release notes ( #16401 )
...
* add: performance improvements to release notes
* fix: mention which endpoint is getting faster
* fix: clarify that reported latency is end-to-end
2025-11-08 16:42:58 -08:00
20180ff93b
[Docs] litellm content filter guard ( #16413 )
...
* add gif 1
* add guard 2
* add guard 3
* guard 5
* docs fix
* docs fix
2025-11-08 16:30:13 -08:00
86d73c918c
Adds support for returning Azure Content Policy error information when exceptions from Azure OpenAI occur ( #16231 )
...
* add provider_specific_fields to ContentPolicyViolationError
* use provider_specific_fields in ProxyException
* update openai_exception_handler
* fix use exception checker for content policy violation azure
* add AzureOpenAIExceptionMapping
* test_azure_with_content_safety_error
* Accessing Provider-Specific Error Details
* TestExceptionCheckers
* unit test got provider_specific_fields=
* add clear types for error dict
* fix test_azure_with_content_safety_error
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com >
2025-11-08 16:04:36 -08:00
e037d9315d
Add Vertex and Gemini Videos API with Cost Tracking + UI support ( #16323 )
...
* Use video id for videos api
* remove mock code
* Potential fix for code scanning alert no. 3630: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* remove print statements
* Update video prefix for 'video_'
* Add veo with openai videos unified specs
* Add videos testing to UI
* remove mock code
* Remove not need ui changes:
* Fix mypy errors related to gemini
* fix test_transform_video_create_request
* Add vertex ai veo config
* Add vertex ai veo config
* Add cost tracking for gemini and add optional param passing
* fix bugs related to vertex ai veo
* Add Gemini Veo Video Generation in Openai Videos Unified Spec (#16229 )
* Add veo with openai videos unified specs
* Add videos testing to UI
* remove mock code
* Remove not need ui changes:
* Fix mypy errors related to gemini
* fix test_transform_video_create_request
* Add contant video duration for gemini and vertex
* Fix litellm_mapped_tests tests
* fix azure videos issue
* Added doc for videos vertex ai
* fix seconds param error
* fix lint errors
* test_transform_video_create_response_cost_tracking_no_duration
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com >
2025-11-08 16:03:51 -08:00
30873688f2
docs: Add documentation for Anthropic memory tool ( #16388 )
2025-11-08 12:38:57 -08:00
bae1857787
fix doc
2025-11-08 10:31:19 -08:00
d65a29b88d
docs: fix image generation response format from 'image' to 'images' ( #16378 )
...
Update documentation to reflect actual API response format:
- Change singular 'image' field to plural 'images' array
- Add complete ImageURLListItem structure with index and type fields
- Update all code examples to use message.images instead of message.image
- Fix streaming examples to access images[0]["image_url"]["url"]
The documentation was incorrectly showing 'image' (singular object)
but the actual implementation returns 'images' (array of ImageURLListItem).
Related to issue #16227
2025-11-07 19:06:03 -08:00
532ebf43d0
docs(moderation.md): fix moderation quick start docs
2025-11-07 16:25:08 -08:00
faae0ff0dc
Fix Azure DALL-E-3 health check content policy violation by using safe default prompt ( #16329 )
...
* Add custom health check prompt support
* Add constant for health check prompt
* Add constant for health check prompt
2025-11-07 15:30:56 -08:00
9059905d25
docs(openai/videos.md): document proxy usage on openai docs for video gen
2025-11-07 15:27:18 -08:00
2bd85dc455
[Feat] Add DD Agent Host support for datadog callback ( #16379 )
...
* add DD_AGENT_HOST
* docs DD Agent
* test_datadog_agent_configuration
* DD_AGENT_HOST
2025-11-07 15:18:23 -08:00
a6b0993405
[Feat] Secret Manager - Hashicorp, add auth via approle ( #16374 )
...
* add _verify_required_credentials_exist and _auth_via_approle
* test_hashicorp_secret_manager_approle_auth
* docs hcorp auth
2025-11-07 14:39:33 -08:00
ea4048324b
docs fix
2025-11-07 14:39:24 -08:00
5733f711fd
feat(guardrails): panw prisma airs guardrail deduplication and enhanced session tracking ( #16273 )
...
* feat(guardrails): Add deduplication and session tracking
- Implement deduplication logic to prevent duplicate scans (via call_id; add _check_and_mark_scanned) caused by LiteLLM callback system
- Add session tracking using litellm_trace_id as AI Session ID for Prisma AIRS SCM logging
- Extract helper methods _extract_prompt_from_request maintainability
- Use httpxSpecialProvider import (LoggingCallback -> GuardrailCallback)
- Add comprehensive tests for deduplication and session tracking (7 new tests)
- Update documentation with multi-turn conversation tracking examples
* docs: update PANW Prisma AIRS multi-turn conversation example to use industry-standard terminology
- Clearer example for conversation tracking
- Updated terminology from 'AI Session ID' to 'Prisma AIRS AI Session ID' for clarity
* fix: remove unused asyncio import
* fix: correct mypy type ignore comment
2025-11-06 19:34:37 -08:00
83998d3573
Update the fireworks url in tests and doc ( #16346 )
2025-11-06 19:22:21 -08:00
a05159dc6e
docs fix
2025-11-06 17:21:23 -08:00
830a9e9585
docs fix
2025-11-06 16:22:17 -08:00
Cesar Garcia