API Guide | JoyToken | Documentation

JoyToken currently exposes an OpenAI-compatible model gateway for developers. Point your OpenAI SDK or HTTP client base URL at JoyToken to integrate.

Public Endpoints

Endpoint	Auth	Use
`POST /openai/v1/chat/completions`	API key required	Chat completions with non-streaming and SSE streaming support
`GET /api/v1/models`	No API key required	Public model catalog

Base URLs

Scenario	Base URL
OpenAI-compatible model calls	`JOY_TOKEN_OPENAI_BASE_URL` from Environments
JoyToken API	`JOY_TOKEN_API_BASE_URL` from Environments

Authentication

Authorization: Bearer $JOY_TOKEN_API_KEY

For compatibility with older clients:

X-API-Key: $JOY_TOKEN_API_KEY

Do not send both Authorization and X-API-Key on the same request. If both are present, the current gateway reads X-API-Key first.

Minimal Request

$ curl "$JOY_TOKEN_OPENAI_BASE_URL/chat/completions" \
>   -H "Content-Type: application/json" \
>   -H "Authorization: Bearer $JOY_TOKEN_API_KEY" \
>   -H "X-Request-ID: quickstart-001" \
>   -d '{
>     "model": "auto",
>     "messages": [
>       { "role": "user", "content": "Reply with exactly: pong" }
>     ],
>     "stream": false
>   }'

Response Fields to Check

Field	Location	Use
`choices[0].message.content`	Body	Model output
`usage`	Body	Token and cost statistics
`metadata.billing`	Body / streaming metadata	JoyToken billing details
`X-DAOE-Used-Model`	Response header	Actual selected model
`X-DAOE-Used-Provider`	Response header	Actual provider
`X-Request-ID`	Request header	Log and debugging correlation