Quick start

Drop a config, start the server, call it like OpenAI.

1 · config & run

cp models.yaml ~/.config/routsi/   # or keep ./models.yaml
routsi serve                       # listens on :11080
routsi serve -port 9000            # …or override the port

2 · call it (any OpenAI SDK works)

curl localhost:11080/v1/chat/completions \
  -H 'content-type: application/json' \
  -d '{"model":"auto","messages":[{"role":"user","content":"hello"}]}'

3 · choose your next guide

• Devin — use the built-in direct Devin provider.
• Claude on AWS — use Bedrock with your AWS credential chain.
• Custom adapters — add a command or JavaScript-backed provider.
• S3 analytics — capture and aggregate request, token, latency, and routing data.

Continue: Core concepts →