Cesar Garcia c892c2c83d fix(anthropic): use dynamic max_tokens based on model (#17900) ... * fix(anthropic): use dynamic max_tokens based on model When users don't specify max_tokens in requests to Anthropic models, LiteLLM now uses the correct max_output_tokens value from the model pricing JSON instead of a hardcoded 4096. This fixes truncated responses for Claude 3.5+ models which support higher output limits (8192 for Claude 3.5, 128k for Claude 3.7, etc.) Fixes #8835 * fix(anthropic): restore env var support for backwards compatibility Keep DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS as fallback when model is not found in JSON, allowing users to configure via environment variable.		2025-12-14 08:31:27 +05:30
..
amazon_nova/chat	[New Model] Add Amazon Nova as first party provider for chat completions (#17351)	2025-12-06 14:43:55 -08:00
anthropic	fix(anthropic): use dynamic max_tokens based on model (#17900)	2025-12-14 08:31:27 +05:30
azure	[Fix] CI/CD – Clean Up Performance PR Changes & others (#17838)	2025-12-11 12:50:03 -08:00
azure_ai	fix(azure_ai): Remove unsupported params from Azure AI Anthropic requests (#17822)	2025-12-11 08:09:13 -08:00
baseten/chat
bedrock	Merge pull request #17873 from BerriAI/litellm_rerank_foraward_headers	2025-12-12 22:25:57 +05:30
bytez/chat
chat
cohere	fix(unified_guardrail.py): support during_call event type for unified guardrails (#17514)	2025-12-04 22:06:13 -08:00
cometapi/chat
compactifai
custom_httpx	🐛 Fix proxy caching between requests in aiohttp transport (#17122)	2025-12-02 14:37:45 -08:00
dashscope
databricks	Update Databricks model pricing and add new models (including databricks pricing test). (#17277)	2025-12-01 20:06:47 -08:00
datarobot
deepgram
deepinfra
docker_model_runner	fix docker model runner tests	2025-11-22 11:07:56 -08:00
featherless_ai/chat
fireworks_ai	Add fireworks rerank support	2025-12-08 20:29:50 +05:30
gemini	fix: add speechConfig to GenerationConfig for Gemini TTS (#17851)	2025-12-12 03:56:44 -08:00
github_copilot	fix(github_copilot): preserve encrypted_content in reasoning items for multi-turn conversations (#17130)	2025-12-05 12:42:25 -08:00
heroku
hosted_vllm
huggingface
jina_ai/embedding
lemonade
litellm_proxy/chat
llamafile/chat
lm_studio
meta_llama
mistral
moonshot
nebius
novita/chat
nscale/chat
oci/chat	OCI Provider: Fix pydantic validation errors during tool call with streaming. (#16899)	2025-11-23 22:03:44 -08:00
ollama	Fixes #13652 - auth not working with ollama.com (#17191)	2025-12-05 15:52:54 -08:00
openai	feat(openai): add reasoning_effort='xhigh' support for gpt-5.2 models (#17875)	2025-12-12 11:40:35 -08:00
openai_like	Refactor: Skip PublicAI tests if API key is not set (#17540)	2025-12-05 10:22:07 -08:00
openrouter/chat	Support Deepseek 3.2 with Reasoning (#17384)	2025-12-02 22:00:19 -08:00
ovhcloud	Add support of audio transcription for OVHcloud (#17305)	2025-12-01 18:26:39 -08:00
perplexity	fix(perplexity): use API-provided cost instead of manual calculation (#17887)	2025-12-14 08:24:44 +05:30
pg_vector/vector_stores
publicai	Fix: Lack of None value checks & update publicai_chat_transformation tests (#17539)	2025-12-05 09:43:52 -08:00
ragflow/chat	fix failing vertex tests	2025-12-06 00:04:04 +05:30
recraft
runwayml
sagemaker
sambanova
sap	[New provider] Sap gen ai hub (#16053)	2025-12-08 12:31:06 -08:00
snowflake
stability	feat(stability): add Stability AI image generation support (#17894)	2025-12-14 08:29:45 +05:30
vercel_ai_gateway
vertex_ai	fix gemini web search requests count (#17921)	2025-12-14 08:18:26 +05:30
volcengine
voyage/rerank	[Fix] CI/CD – Clean Up Performance PR Changes & others (#17838)	2025-12-11 12:50:03 -08:00
wandb
watsonx	[Bug Fix] Watsonx Audio Transcription - ensure only correct params are sent to API (#17840)	2025-12-11 15:21:09 -08:00
xai	Prompt security litellm (#16365)	2025-11-24 11:44:20 -08:00
zai	feat(provider): add Z.AI (Zhipu AI) as built-in provider (#17307)	2025-12-01 19:56:47 -08:00