# telemetry.dev

> Hosted observability for AI/LLM apps. Product line: every model call, tool step, and retrieval in one OpenTelemetry trace, with tokens, cost, latency, and errors. Ingest via TypeScript or Python SDKs, or any OTLP exporter. Cost is computed server-side against 4700+ models.

- Slug: telemetry-dev
- Record: cmp_telemetry-dev
- Kind: resource
- Functions: ingest, observe, retrieve
- Score: 9
- Observed sample: This component is not in Leyline's observed sample.

JSON: https://staging.leyline.ahensya.com/api/v1/components/telemetry-dev