Sentry

Add LLM traces to Sentry performance monitoring

Sentry broadcast sends OTLP spans with model usage and finish-reason metadata. This is useful for correlating AI events with application errors and transaction traces.

broadcast-sentry-config.json

{
  "destination": "sentry",
  "enabled": true,
  "otlp_traces_endpoint": "https://o123.ingest.us.sentry.io/api/456/integration/otlp/v1/traces",
  "dsn": "https://abc123@o123.ingest.us.sentry.io/456",
  "sampling_rate": 1
}

cURL

curl https://api.therouter.ai/v1/chat/completions   -H "Authorization: Bearer $THEROUTER_API_KEY"   -H "Content-Type: application/json"   -H "X-TheRouter.ai-Broadcast: true"   -d '{
    "model":"anthropic/claude-sonnet-4.5",
    "messages":[{"role":"user","content":"Debug this stack trace"}],
    "trace":{"trace_name":"Sentry Trace Test","release":"v2.1.0"}
  }'

Verification

In Sentry Performance, confirm a new transaction/span exists and includes your custom trace metadata keys.