Summary
Vercel added a dedicated AI Gateway Logs page that lists every request a team sends through the gateway with cost, token counts, duration, and the model, provider, and region that served it, plus URL-shareable filters, a request-volume chart, and CSV or JSON export.
What changed
AI Gateway now has a dedicated Logs page showing every request with total cost, a token breakdown across input, output, reasoning, and cache, duration and time to first token, and the serving model, provider, and region; users can filter by provider, model, modality, credentials, or status, share filtered views by URL, zoom a request-count chart, and export to CSV or JSON at team or project scope.
Why it matters
Per-request cost, token, and fallback-path visibility turns multi-provider gateway traffic from a black box into an auditable log, letting teams attribute spend, debug routing and fallbacks, and share exact filtered views without exporting to a separate observability stack.
Evidence excerpt
AI Gateway has a dedicated Logs page 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. Every filter is stored in the URL, so you can share a filtered view by copying the address. You can export the current view as CSV or JSON.