List all LLM models from LiteLLM server with database fallback.
Models are fetched dynamically from the configured LiteLLM server with caching for performance. Falls back to database models if LiteLLM is unavailable.
Query Parameters:
Example:
GET /api/v1/models
GET /api/v1/models?provider=xai
GET /api/v1/models?runtime=claude_code
Filter by provider (e.g., 'xai', 'anthropic')
Filter by compatible runtime (e.g., 'claude_code')
x >= 01 <= x <= 1000Successful Response