Export AI Gateway traces with Vercel Drains
Vercel AI Gateway can export per-request OpenTelemetry traces, exposing routing, retries, latency, tokens, cost, and attribution without sending prompt or completion content.
AI Gateway now emits **one OpenTelemetry trace per request**. Pro and Enterprise teams can export traces through Vercel Drains to OTLP/HTTP endpoints, with routing, fallbacks, retries, usage, cost, latency, status, and deployment attribution included.
Send sampled traces to the observability system you already use, then inspect provider failover, slow first tokens, and unexplained agent costs alongside application telemetry. Prompt and completion content are excluded from the drain.
AI Gateway now emits **one OpenTelemetry trace per request**. Pro and Enterprise teams can export traces through Vercel Drains to OTLP/HTTP endpoints, with routing, fallbacks, retries, usage, cost, latency, status, and deployment attribution included. Send sampled traces to the observability system you already use, then inspect provider failover, slow first tokens, and unexplained agent costs alongside application telemetry. Prompt and completion content are excluded from the drain. Export costs **$0.05 per 1,000 delivered traces per drain**, plus **$0.50 per GB** transferred. Multiple provider attempts still count as one request, but sending the same request to multiple drains creates separate delivery charges.
This extends AI Gateway observability from a Vercel-hosted request view into sampled, application-wide telemetry pipelines. Teams can correlate routing, failover, latency, and cost with deployments without exporting prompt content, but must now make explicit sampling, retention, and multi-drain cost choices; it improves diagnosis, not enforcement or remediation.