API Reference

Endpoints

POST /v1/chat/completions

OpenAI-compatible chat completions.

curl http://localhost:8003/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"VibeThinker","messages":[{"role":"user","content":"hello"}],"max_tokens":100}'

GET /v1/models

List available models.

curl http://localhost:8003/v1/models

GET /stats

Request statistics: requests, errors, cache hits/misses.

curl http://localhost:8003/stats

Environment