Quickstart
Send your first chat completion request.
Create an API key
Create a key in Token Management, copy it immediately, and keep it server-side. Keys carry billing authority for the balance they belong to.
Choose a model
Copy a public model ID from the Models page. The example below uses gpt-5.6-sol; replace it with a model currently available to your account when necessary.
Send a request
The examples call http://127.0.0.1:11113 directly.
curl "http://127.0.0.1:11113/v1/chat/completions" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.6-sol",
"messages": [{ "role": "user", "content": "Hello" }],
"stream": true
}'Read the result
With stream: true the response is a text/event-stream. Each event carries a delta; the stream ends with data: [DONE]. Open Request Logs to confirm the final status, usage, and charge.
Keep keys off the browser
Never ship a key to client-side code. Proxy requests through your own backend.
Help us improve this page
Found something unclear, outdated, or incorrect?
Last updated on