Datadog

Observe LLM quality and cost in Datadog alongside app telemetry

Datadog broadcast emits spans with GenAI semantic attributes and usage metrics. This is useful for model-level SLOs, cost dashboards, and incident investigations.

broadcast-datadog-config.json

{
  "destination": "datadog",
  "enabled": true,
  "api_key": "dd_...",
  "ml_app": "customer-support-prod",
  "url": "https://api.us5.datadoghq.com",
  "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":"openai/gpt-4.1-mini",
    "messages":[{"role":"user","content":"Summarize customer sentiment"}],
    "user":"user_42",
    "trace":{"trace_name":"Datadog Trace Check","team":"support"}
  }'

Verification

In Datadog, search LLM Observability traces by your `ml_app` service tag and confirm custom metadata appears in span meta.