Responses

Response Format

Understanding the Messages API response structure and handling.

Response Structure

{
  "id": string,
  "object": "chat.completion",
  "created": integer,
  "model": string,
  "choices": [
    {
      "index": integer,
      "message": {
        "role": string,
        "content": string
      },
      "finish_reason": string
    }
  ],
  "usage": {
    "prompt_tokens": integer,
    "completion_tokens": integer,
    "total_tokens": integer
  }
}

Response Fields

• id- Unique identifier for the completion

• object- Type of object returned

• created- Unix timestamp of when the completion was created

• model- Model used for completion

• choices- Array of completion choices:

• • index- Index of the choice

  • message- The completion message object

  • finish_reason- Why the completion stopped

• usage- Token usage statistics

Example Response

{
  "id": "chatcmpl-123abc",
  "object": "chat.completion",
  "created": 1702142465,
  "model": "Reverix-Prod",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here's a Python function to calculate Fibonacci numbers:\n\ndef fibonacci(n):\n    if n <= 1:\n        return n\n    return fibonacci(n-1) + fibonacci(n-2)"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 42,
    "total_tokens": 67
  }
}

Streaming Responses

When streaming is enabled, the API sends chunks in the following format:

data: {
  "id": "chatcmpl-123abc",
  "object": "chat.completion.chunk",
  "created": 1702142465,
  "model": "Reverix-Prod",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": "Here's"
      },
      "finish_reason": null
    }
  ]
}

data: {
  "id": "chatcmpl-123abc",
  "object": "chat.completion.chunk",
  "created": 1702142465,
  "model": "Reverix-Prod",
  "choices": [
    {
      "index": 0,
      "delta": {
        "content": " a"
      },
      "finish_reason": null
    }
  ]
}