Documentation

Connect with the client you already use

Overagent follows the OpenAI chat completions contract. Replace the base URL and API key, then keep your existing request and streaming code.

01 · Quickstart

Send the first request

Use a server-side API key created from the dashboard. Never expose it in browser code.

curl http://localhost:4000/v1/chat/completions \
  -H "Authorization: Bearer sk-oa_..." \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-4-6","messages":[{"role":"user","content":"Hello"}]}'
02 · Authentication

Bearer API keys

Send the key in the Authorization header. The secret is shown once at creation and stored only as a hash after that.

03 · Endpoints
GET/v1/modelsList the models enabled for your key.
POST/v1/chat/completionsCreate a standard or streaming completion.
GET/healthCheck gateway, database, and queue health.
04 · Streaming

Server-sent events

Set stream to true to receive OpenAI-compatible data chunks followed by data: [DONE].

05 · Billing

Prepaid and settled per request

Each request reserves an estimate, then settles to its recorded usage. Any unused reservation returns to the wallet automatically.