ai-agents-provider-mapping-when-using-openrouter-as-the-provider-for-embeddin-354932ae

THEN Update LiteLLM's provider mapping to include OpenRouter as a valid provider for embeddings. As a temporary workaround, bypass LiteLLM and call the OpenRouter embeddings endpoint directly via curl. Submit a PR to LiteLLM to add the mapping for OpenRouter embeddings.

Error observed:
$ curl http://192.168.233.1:4000/v1/embeddings -H "Content-Type: application/json" -d '{"input": "test sentence", "model": "test-model"}'
Response: {"error":{"message":"litellm.BadRequestError: Unmapped LLM provider for this endpoint. You passed model=qwen/qwen3-embedding-8b, custom_llm_provider=openrouter..."}}
Direct API call that works:
$ curl https://openrouter.ai/api/v1/embeddings -H "Authorization: Bearer <API key>" -H "Content-Type: application/json" -d '{"input": "test sentence", "model": "qwen/qwen3-embedding-8b"}'