Response Schema

Orbyt returns a unified response format derived from the OpenAI specification. This ensures that every downstream model integration behaves predictably across your infrastructure.

Completion Object

The execution engine normalizes provider-specific responses into a single, standardized JSON structure.

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4-0613",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I am a helpful assistant."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Performance Metrics

The usage block provides precise tracking of token consumption. These metrics are calculated by the gateway as responses stream from the underlying providers.