[FEATURE]: Detect model(s) using the /v1/models route on custom provider

When we try to add a custom provider, an open-ai compatible one (vllm in my case), we need to put manually the id of the model or models name:

but when we do the same on kilo code, this one automatically detects the model(s):

magic? no ! kilo just use the old and good /v1/models route:

please implements the same feature of kilo code

This issue might be a duplicate of existing issues. Please check:

[FEATURE]: Hydrate custom provider model metadata from /v1/models and Models.dev #25407: Requests the same feature — hydrating/discovering models from /v1/models on custom OpenAI-compatible providers
[FEATURE]:LM Studio provider should auto-detect models via /v1/models API (similar to Continue extension) #23327: Requests auto-detection of models via /v1/models for LM Studio (same underlying mechanism)
[Feature Request]: Allow dynamic model passthrough for custom OpenAI-compatible providers without explicit declaration #18219: Requests dynamic model passthrough / auto-discovery for custom OpenAI-compatible providers without explicit declaration

Please review these issues and consider adding a "+1" or additional context there rather than opening a new request.

To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.

Navigation Menu