Sign InOpen Brain
VercelEngineering PostOfficial Source

AI Gateway logs now have a dedicated page

AI Gateway’s dedicated logs expose per-request cost, tokens, latency, routing, and provider fallbacks, making agent failures and spend anomalies easier to trace.

Vercel · Jul 31, 2026
Open Source Open MarkdownOpen JSON
Source Summary

The new **Logs page** lists gateway requests with cost, token counts, duration, model, provider, and region. Request details include time to first token, cache and reasoning tokens, policy flags, and the ordered fallback path.

Practical Implication

Use filters and request-ID search to debug agent failures or compare routing behavior. Filtered views are shareable by URL and exportable as **CSV or JSON**, which makes targeted cost and reliability analysis easier.

Agent-Ready Context
The new **Logs page** lists gateway requests with cost, token counts, duration, model, provider, and region. Request details include time to first token, cache and reasoning tokens, policy flags, and the ordered fallback path.

Use filters and request-ID search to debug agent failures or compare routing behavior. Filtered views are shareable by URL and exportable as **CSV or JSON**, which makes targeted cost and reliability analysis easier.

The page records what happened but does not define alerts, retention, or automated remediation. Diagnosis still requires interpreting provider failures, routing-budget exhaustion, and latency in the context of the agent run.
Connected Context · Feed7 Judgment

This turns gateway observability into a request-level diagnostic surface: teams can inspect routing, fallbacks, latency, tokens, policy flags, and cost together, then export or share the evidence. It complements controls and serving options in the prior candidates, but does not close the operational loop because alerting, retention, interpretation, and remediation remain outside the page.

AI Gateway now supports team and project spend budgetsBudgets enforce cost boundaries, while the logs provide request-level evidence for explaining spend and determining whether a run stopped after exhausting an applicable budget.AI Gateway adds unified fast mode supportFast mode must be verified through routing metadata; the logs expose model, provider, duration, and fallback details needed to check whether the requested tier was actually used.Claude Fable 5 access restored on AI GatewayThe model’s stricter refusals make fallback design important, and the ordered fallback path plus policy flags provide evidence for diagnosing those routing outcomes.From Signal to PR: Anatomy of a Self-Improving Agent — Jason Lopatecki, ArizeThe production-trace workflow requires inspectable run evidence; this page supplies gateway-level data that can feed investigations, while leaving issue interpretation and fixes to the broader agent workflow.
Context Map
infracodingdata#observability#gateways#agent-reliability
Uncertainty
The page records what happened but does not define alerts, retention, or automated remediation. Diagnosis still requires interpreting provider failures, routing-budget exhaustion, and latency in the context of the agent run.