Skip to main content
The SDK sends batched telemetry events to this endpoint. Direct use is possible, but the SDK is recommended because it handles batching, retries, context propagation, and rule interactions.

​
Request

{
  "batch_id": "batch_01hxyz",
  "events": [
    {
      "trace_id": "trace_123",
      "span_id": "span_123",
      "timestamp": "2026-06-11T10:00:00.000Z",
      "customer_id": "cust_abc123",
      "step_name": "evaluate",
      "provider": "openai",
      "model": "gpt-4o-mini",
      "tokens_in": 1200,
      "tokens_out": 320,
      "latency_ms": 842,
      "status": "success"
    }
  ]
}

​
Response

{
  "accepted": 1,
  "rejected": 0
}
The response can include validation errors, pricing warnings, and budget flags when applicable.

​
Notes

  • Cost is calculated server-side.
  • Duplicate span IDs in a batch are ignored.
  • Events with unknown pricing can be accepted and surfaced as pricing setup tasks.
  • Do not include prompts, completions, raw messages, emails, or API keys in event metadata.