Ready

Readiness — is the LLM provider reachable?

GET/api/v1/ready

Readiness check: is the service ready to accept requests? Actually pings the LLM provider. No parameters.

Response (reachable)

json

{
  "status": "ok",
  "version": "1.0.0",
  "environment": "development",
  "provider": "deepseek",
  "provider_reachable": true
}

If the upstream does not answer, status becomes degraded and provider_reachable false — the HTTP status stays 200 regardless.

json

{ "status": "degraded", "provider_reachable": false }

Read the status, not the 200

For load balancers and deploy gates, status/provider_reachable is authoritative, not the HTTP code.

200

Always 200 — the state is in the body.