Chat Completions

OpenAI-compatible chat completions endpoint.

Endpoint

POST /api/v1/chat/completions

Request

{
  "model": "openai/gpt-5",
  "messages": [
    { "role": "user", "content": "Write a haiku about APIs." }
  ]
}

curl

curl https://your-domain.com/api/v1/chat/completions \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [
      { "role": "user", "content": "Write a haiku about APIs." }
    ]
  }'

Notes

Only models returned by /api/v1/models can be used.
Credits are deducted only after the upstream request succeeds.
The request is rejected before execution if the API key scope or rate limit fails.

On this page