Observability added to AI Gateway alpha
Vercel just made multi-model routing invisible. Now you see the cost of every token, every model, every request.
Why it matters
Vercel's AI Gateway observability layer removes the black box from multi-model LLM deployments, letting builders optimize for latency, cost, and performance across ~100 models in real time. This is infrastructure-as-a-feature for the app-layer.
The key facts
11 to knowVercel AI Gateway supports ~100 models
New observability dashboard tracks: requests by model, time to first token (TTFT), request duration, input/output token count, cost per request
Observability available across all projects or per-project/per-model drill-down
Cost tracking free during alpha phase
Feature currently in alpha
Vercel AI Gateway alpha supports ~100 models
New observability dashboard tracks: requests by model, time-to-first-token (TTFT), request duration, input/output token counts
Cost-per-request visibility included (free during alpha)
Per-project and per-model drill-down capability
Feature enables direct model performance and latency comparison
Published June 9, 2025
Go to the source
Vercel Blogvercel.com
Publisher excerpt: The , currently in alpha for all users, lets you switch between ~100 AI models without needing to manage API keys, rate limits, or provider accounts.AI Gateway now includes a dedicated AI section to surface metrics related to the AI Gateway. This update introduces visibility into:Vercel…