Skip to Content

Vercel AI Gateway usage and spend

Vercel AI Gateway observability shows request volume, latency, token usage, and spend across providers in one dashboard.

Hub: Tokenminning with Vercel AI Gateway.

Open the dashboard

  1. Go to vercel.com/dashboard 
  2. Select your project → AI GatewayObservability
  3. Filter by model, provider, and time range

See observability docs  for metrics reference.

Usage and billing

Usage and billing  explains pricing: zero markup on tokens. BYOK uses your provider keys at provider rates.

ModeCost
AI Gateway keyProvider rates, no markup
BYOKYour provider contract rates

App attribution

Track which apps drive spend with app attribution  headers. Tag requests by feature, route, or deployment.

Separate environments

EnvironmentPattern
PreviewSeparate AI Gateway key or budget alert
ProductionProduction key with spend monitoring
Local devDirect provider keys or local Ollama

Spending guardrails

  • Review observability weekly — which model slug dominates?
  • Set alerts before monthly budget thresholds
  • Use BYOK only when enterprise contracts beat gateway pooling
  • Attribute spend per app with attribution headers
Last updated on