Request & Response Format

Request Format

All requests use JSON and require these headers:

Content-Type: application/json
Authorization: Bearer YOUR_API_KEY

Successful Responses

Response shapes vary by endpoint, each following its own API spec:

Chat Completions — OpenAI standard response format
Claude Messages — Anthropic standard response format
Gemini — Google standard response format
Asynchronous Tasks — QWave API unified task response format

Billing Field (usage.cost)

The OpenAI-format responses from /v1/chat/completions and /v1/embeddings return the call’s billed quota in usage.cost. Its unit is quota (an integer), not US dollars (USD). For example, cost: 150 means 150 quota.

{
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 8,
    "total_tokens": 20,
    "cost": 150
  }
}

Non-streaming Chat Completions and Embeddings → usage.cost in the response body
Streaming Chat Completions (SSE) → the last data frame carrying usage (see Streaming)

Claude Messages (/v1/messages), OpenAI Responses (/v1/responses), and native Gemini endpoints use their own usage structures. They do not currently define a shared gateway usage.cost field. Do not interpret an upstream field with the same name as gateway quota; check these calls’ charges in the console usage records. Async tasks have separate cost and settlement-status fields; see Query Task. Do not add task cost fields directly to text usage.cost as though their units were the same.

Error Responses

Error structures differ slightly across endpoints: Synchronous endpoints (chat / messages / images, etc.) — OpenAI-compatible format with a type field:

{
  "error": {
    "message": "Detailed error description",
    "type": "invalid_request_error",
    "code": "invalid_request"
  }
}

Asynchronous task endpoints (/v1/tasks/...) — Simplified format with only message + code:

{
  "error": {
    "message": "Detailed error description",
    "code": "task_failed"
  }
}

Status Codes

Code	Meaning	How to Handle
400	Invalid request parameters	Check the request payload
401	Authentication failed	Verify your API key
402	Insufficient balance	Top up your account
404	Task or resource not found	Verify the task_id and that it belongs to your account
429	Rate limit exceeded / sliding-window quota exhausted (`code: quota_window_exceeded`, response includes `window`/`used`/`cap`/`reset_at`)	Reduce frequency or retry after `reset_at`
500	Internal server error	Retry later

Getting Started

Core Concepts

Request & Response Format

Request Format

Successful Responses

Billing Field (usage.cost)

Error Responses

Status Codes

​Request Format

​Successful Responses

​Billing Field (usage.cost)

​Error Responses

​Status Codes

Request Format

Successful Responses

Billing Field (usage.cost)

Error Responses

Status Codes