AI Gateway logs now have a dedicated page
Vercel ships observability into AI Gateway: per-request logs, cost tracking, and fallback routing visibility.
Why it matters
AI Gateway's new dedicated logs page gives practitioners real-time visibility into API costs, token usage, routing decisions, and provider failures — table-stakes observability for teams managing multi-provider AI workloads in production.
The key facts
12 to knowVercel AI Gateway logs page now lists every request with cost, token counts, duration, model, provider, region
Filters: provider, model, modality, credentials, status; searchable by model, provider, request ID
Per-request drill-down shows token breakdown (input, output, reasoning, cache reads/writes), time-to-first-token, Zero Data Retention and region restrictions applied
Fallback path visibility: lists every provider attempt in order with status codes, credentials, duration, and failure reasons
Export as CSV or JSON with filters applied; URL-shareable filtered views; time-range charting with zoom
Available at team scope and per-project scope
AI Gateway logs page shows per-request cost, token counts, duration, model, provider, region
Filters by provider, model, modality, credentials, status; searchable by model/provider/request ID
Request details include token breakdown (input, output, reasoning, cache), time-to-first-token, fallback path with provider attempts and failure reasons
Exports as CSV or JSON; chart shows request volume over time with zoom capability
Available at team scope and per-project
Zero Data Retention and region restrictions applied per request
Go to the source
Vercel Blogvercel.com
Publisher excerpt: AI Gateway now has a dedicated listing every request your team sends through the gateway, newest first, with cost, token counts, duration, and the model, provider, and region that served it. Open any request to see how it was routed. It's available at the team scope and per project.Logs page Filter…