vLLM API Gateway
OpenAI-compatible inference proxy
● Online
Authentication
AUTH
Bearer token required for POST endpoints —
Authorization: Bearer <VLLM_API_KEY>
Endpoints
GET
/health
GET
/v1/models
POST
/v1/chat/completions
POST
/v1/completions
vLLM
GET
/vllm/docs
GET
/vllm/openapi.json
Observability
GET
/api/langfuse-tracing
API Documentation
GET
/api/documentation