API reference

OpenAI-compatible endpoints.

Authentication

Send Authorization: Bearer <API_KEY> on every request. Keys can be created and revoked in the console.

Authorization: Bearer sk-...

Endpoints

Chat Completions

POST /v1/chat/completions
Content-Type: application/json

{
  "model": "gpt-6.1-sol",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}

{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "model": "gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Hello!"},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 5,
    "total_tokens": 23
  }
}

Streaming

Set stream: true to receive SSE. The proxy is configured with proxy_buffering off.

data: {"choices":[{"delta":{"content":"Hel"}}]}
data: {"choices":[{"delta":{"content":"lo"}}]}
data: [DONE]

Rate limits

RPM / TPM are set per plan and shown in the console.

Limits are examples. Actual limits are shown in the console and the contract.