Feature hasn't been suggested before.
Describe the enhancement you want to request
LiteLLM is an open-source proxy that provides a unified OpenAI-compatible API in front of 100+ LLM providers, with load balancing, spend tracking, and rate limiting.
Users can already use LiteLLM via the custom provider flow, but that requires manually adding each model. Since LiteLLM exposes a /v1/models endpoint, a built-in provider could
auto-discover all available models from the proxy at startup.
The integration would work by setting LITELLM_BASE_URL and optionally LITELLM_API_KEY env vars. LiteLLM is a gateway/proxy, so it doesn't fit the models.dev pattern - the available models depend on what the user has configured on their proxy.
I have a working implementation ready to submit as a PR.
Feature hasn't been suggested before.
Describe the enhancement you want to request
LiteLLM is an open-source proxy that provides a unified OpenAI-compatible API in front of 100+ LLM providers, with load balancing, spend tracking, and rate limiting.
Users can already use LiteLLM via the custom provider flow, but that requires manually adding each model. Since LiteLLM exposes a /v1/models endpoint, a built-in provider could
auto-discover all available models from the proxy at startup.
The integration would work by setting LITELLM_BASE_URL and optionally LITELLM_API_KEY env vars. LiteLLM is a gateway/proxy, so it doesn't fit the models.dev pattern - the available models depend on what the user has configured on their proxy.
I have a working implementation ready to submit as a PR.