Sameer Kankute
e0396e5fa7
Merge pull request #17082 from BerriAI/main
...
merge main
2025-11-25 18:49:52 +05:30
Sameer Kankute
afe540e88d
Fix auth issue
2025-11-25 18:26:25 +05:30
Mubashir Osmani
a807fe4450
add claude opus 4.5 ( #17043 )
...
* add claude opus 4.5
* Apply suggestion from @Chesars
Co-authored-by: Cesar Garcia <128240629+Chesars@users.noreply.github.com>
---------
Co-authored-by: Cesar Garcia <128240629+Chesars@users.noreply.github.com>
2025-11-24 14:30:36 -08:00
Ishaan Jaffer
9817347013
fix govcloud
2025-11-22 10:46:12 -08:00
Ishaan Jaffer
0ed443f3bd
fix claude-sonnet-4-5-20250929-v1:0
2025-11-22 10:02:15 -08:00
Ishaan Jaffer
eb10dd497d
fix bedrock model info
2025-11-22 09:41:15 -08:00
Ishaan Jaff
661117678c
Revert "remove deprecated embedding model ( #16724 )" ( #16970 )
...
This reverts commit b9bc903536
2025-11-22 09:34:53 -08:00
jlan-nl
7b05a5f9ae
Add full information to vertex_ai/gemini-2.5-flash-image key ( #16882 )
...
Co-authored-by: IQHL (Hans Jacob Landelius) <iqhl@novnordisk.com>
2025-11-21 20:02:02 -08:00
Justin Tahara
703f619e08
feat(bedrock): Add Claude 4.5 to US Gov Cloud ( #16957 )
...
* feat(bedrock): Add Claude 4.5 to US Gov Cloud
* Adding west and tests
2025-11-21 19:06:26 -08:00
Ishaan Jaffer
58a56babd9
test fixes for masker
2025-11-21 17:41:35 -08:00
Cesar Garcia
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
Cesar Garcia
22ef7ab070
feat: Add support for Gemini 3 Pro Image model ( #16938 )
...
Add gemini-3-pro-image-preview model configuration for Google's new
image generation model (aka "Nano Banana Pro 🍌 ").
Model details:
- Input: $2.00/1M tokens (text), $0.0011/image
- Output: $12.00/1M tokens (text), $0.134/image (1K/2K)
- Context: 65k input / 32k output tokens
- Capabilities: structured outputs, web search, caching, thinking
- No function calling support
- Available on both Gemini API and Vertex AI
Added variants:
- gemini-3-pro-image-preview (base, uses Vertex AI)
- gemini/gemini-3-pro-image-preview (Gemini API)
- vertex_ai/gemini-3-pro-image-preview (Vertex AI)
Source: https://ai.google.dev/gemini-api/docs/pricing
Fixes : #16925
2025-11-21 15:55:25 -08:00
Ishaan Jaff
01ea6c8948
[New model] Add GLM 4.6 from together.ai ( #16942 )
...
* new model - add together_ai/zai-org/GLM-4.6
* together_ai/zai-org/GLM-4.6
2025-11-21 14:39:52 -08:00
Cesar Garcia
1812ebae70
fix: Correct Cerebras GPT-OSS-120B model name ( #16939 )
...
Change model identifier from cerebras/openai/gpt-oss-120b to
cerebras/gpt-oss-120b to match Cerebras API requirements.
The Cerebras API only accepts 'gpt-oss-120b' as the model ID, not
'openai/gpt-oss-120b'. The previous name was causing "Model does not
exist" errors when users tried to use it.
Tested with real API calls to confirm:
- cerebras/gpt-oss-120b → sends 'gpt-oss-120b' → ✅ works
- cerebras/openai/gpt-oss-120b → sends 'openai/gpt-oss-120b' → ❌ fails
Fixes #16924
2025-11-21 14:20:31 -08:00
ツルマルツヨシ
be9f2e026c
feat(pricing): Add Gemini 3 Pro Preview for OpenRouter ( #16905 )
2025-11-21 08:52:25 -08:00
Sameer Kankute
c3143e388e
Add thought signature support to v1/messages api ( #16812 )
...
* Add thought signature support to v1/messages api
* update the thinking level handling logic
* update the thinking level handling logic
* Add streaming support
* fix intalling litellm error
2025-11-19 20:24:31 -08:00
Sameer Kankute
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
Sameer Kankute
36c9fede4e
Add azure gpt-5.1 models ( #16817 )
2025-11-19 18:37:08 -08:00
Ishaan Jaff
ffe00f4034
Revert "make all gpt-5 and reasoning models to responses by default ( #16766 )" ( #16849 )
...
This reverts commit 149f308451
2025-11-19 13:32:58 -08:00
Sameer Kankute
149f308451
make all gpt-5 and reasoning models to responses by default ( #16766 )
2025-11-18 20:31:59 -08:00
Marty Sullivan
eb301a7f87
Add Azure models 2025 11 to cost maps ( #16762 )
...
* add gpt-realtime models for azure
* update backup models w/ azure realtime
* add azure gpt-5.1 models to cost map
* add gpt-audio azure models to cost map
* add gpt-4o-transcribe-diarize azure model cost
2025-11-18 19:58:06 -08:00
CatBraaain
9ec31bdd5b
fix: correct wrong system message handling for gemma ( #16767 )
2025-11-18 11:35:56 -08:00
Marty Sullivan
a032b077db
update veo 3 pricing and add prod models ( #16781 )
2025-11-18 11:29:45 -08:00
Sameer Kankute
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
mmandic-coatue
355eff8723
fix haiku-4-5 bedrock configs ( #16732 )
2025-11-17 19:52:01 -08:00
Sameer Kankute
b9bc903536
remove deprecated embedding model ( #16724 )
2025-11-17 18:46:20 -08:00
Sameer Kankute
20ba3fce70
Add deepseek-v3p1-terminus and kimi-k2-instruct in model map for fireworks ai ( #16720 )
2025-11-17 18:30:32 -08:00
Matt Morgis
f9ecf56715
Update Azure Pricing ( #16371 )
...
* add azure eu & us gpt-5 pricing
* add azure us gpt-4.1 pricing
* fix azure/o3-2025-04-16 to match azure/o3
* add azure us o3 pricing
2025-11-15 19:36:13 -08:00
Sameer Kankute
a2e3b942dc
Vector store files Stable Release ( #16643 )
...
* Add support for vector store files endpoints (#16490 )
* Add base code for vector store integration
* fix azure related tests and linting error
* fix mypy errors
* Add vector store files documentation
* fix mapped tests
* Add bytedance and ideogram support in fal ai (#16636 )
* Add fal ai flux pro v1.1 support (#16578 )
* Add fal ai flux pro v1.1 support
* Add tests and docs
---------
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
2025-11-15 13:00:33 -08:00
Emerson Gomes
1dac777346
Add Vertex Kimi-K2-Thinking ( #16671 )
...
* Add Vertex Kimi-K2-Thinking
* Update model_prices_and_context_window.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update litellm/model_prices_and_context_window_backup.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-14 16:49:48 -08:00
fzowl
b1922e19f8
Voyageai pricing and doc update ( #16641 )
...
* Refresh VoyageAI models and prices and context
* Refresh VoyageAI models and prices and context
* Refresh VoyageAI models and prices and context
* Updating the available VoyageAI models in the docs
* Updating the available VoyageAI models in the docs
* Updating the model prices and the docs
2025-11-14 14:09:11 -08:00
Sameer Kankute
52a42e1728
Add all imagen variants in fal ai in model map ( #16579 )
2025-11-13 22:31:49 -08:00
Sameer Kankute
13993d6ea3
Add fal-ai/flux/schnell support ( #16580 )
2025-11-13 22:31:31 -08:00
Ishaan Jaffer
3feae855bd
fix mapped test
2025-11-13 17:00:09 -08:00
Ishaan Jaffer
3c662eadb4
add runwayml/eleven_multilingual_v2 pricing
2025-11-13 16:45:35 -08:00
Sameer Kankute
ea80510f78
[Feat] Day-0, Add gpt-5.1 and gpt-5.1-codex family support ( #16598 )
...
* Add day 0 support for gpt-5.1 models
* Add gpt-5.1-codex day 0 support
* update pricing values
2025-11-13 10:55:54 -08:00
Cesar Garcia
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
Sameer Kankute
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
Matt Cowger
51dc4a8476
fix: add new models, delete repeat models, update pricing. ( #16491 )
...
Added 4 new OpenRouter models:
openrouter/deepseek/deepseek-v3.2-exp
openrouter/minimax/minimax-m2
openrouter/z-ai/glm-4.6
openrouter/z-ai/glm-4.6:exacto ]
Updated openrouter/qwen/qwen3-coder:
Significantly reduced input/output costs (1e-06 → 2.2e-7 / 5e-06 → 9.5e-7)
Reduced max token limits (1,000,000 → 262,100)
Added supports_function_calling flag
Removed 2 duplicated Vertex AI Qwen models (just removed duplicates):
vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas
vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas
2025-11-11 19:11:22 -08:00
Ishaan Jaff
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
Sameer Kankute
6cab77f53f
Added thinking streaming support for mistral ( #16434 )
2025-11-10 18:41:45 -08:00
Artem
3289038089
add kimi k2 thinking ( #16445 )
2025-11-10 15:56:06 -08:00
Sameer Kankute
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
Sumit Tembe
0a527bd1d8
Fix cache_read_input_token_cost for gemini-2.5-flash ( #16354 )
2025-11-07 19:11:10 -08:00
Sameer Kankute
fd95909d9f
Add cohere embed v4 model support ( #16358 )
2025-11-07 19:10:42 -08:00
Emerson Gomes
940a72ceb0
Add Vertex MiniMAX m2 ( #16373 )
2025-11-07 14:27:42 -08:00
huangyf
20d1bed514
fix lobal.anthropic.claude-haiku-4-5-20251001-v1:0 supports_reasoning ( #16263 )
2025-11-06 19:35:57 -08:00
Ishaan Jaffer
79d6f40855
fix gemini-live-2.5-flash-preview-native-audio-09-2025
2025-11-06 17:02:50 -08:00
Sameer Kankute
11508c0339
Remove reasoning support from grok-4 models ( #16265 )
2025-11-05 18:44:05 -08:00
Sameer Kankute
34abb7de1a
Add azure gpt-5-pro in model map ( #16235 )
2025-11-05 18:41:53 -08:00
