1a4ad8bf18
* build(model_prices_and_context_window.json): update all mistral models (besides codestral-mamba) to indicate support for response schema Closes https://github.com/BerriAI/litellm/issues/12012 * fix(route_llm_request.py): if llm router is not initialized, go straight through to litellm sdk Fixes https://github.com/BerriAI/litellm/issues/12008 * test: add unit test * fix(ollama_embeddings): fix unecessary await Fixes https://github.com/BerriAI/litellm/issues/11997 * test: update ollama embedding tests |
||
|---|---|---|
| .. | ||
| anthropic | ||
| azure | ||
| azure_ai/chat | ||
| bedrock | ||
| chat | ||
| cohere/chat | ||
| custom_httpx | ||
| databricks | ||
| datarobot | ||
| deepgram | ||
| featherless_ai/chat | ||
| fireworks_ai/chat | ||
| gemini | ||
| hosted_vllm/chat | ||
| huggingface | ||
| litellm_proxy/chat | ||
| llamafile/chat | ||
| lm_studio | ||
| meta_llama | ||
| mistral | ||
| nebius | ||
| novita/chat | ||
| nscale/chat | ||
| ollama | ||
| openai | ||
| openrouter/chat | ||
| perplexity | ||
| sagemaker | ||
| vertex_ai | ||
| watsonx | ||
| test_volcengine.py | ||