Vercel AI Gateway adds spend caps to API keys
Vercel's AI Gateway now lets teams set dollar-denominated spend caps on individual API keys, with configurable refresh periods and automatic request rejection once a budget is exceeded.
Score breakdown
The feature gives teams a concrete guardrail against runaway AI spend, particularly for autonomous or unsupervised workflows that can consume tokens faster than manual monitoring can catch.
- 01Teams can set a dollar-denominated spend cap on any AI Gateway API key.
- 02Requests on a key are automatically rejected once its budget limit is exceeded.
- 03Spend caps apply across all AI Gateway providers and models running through the key.
Vercel has shipped spend quota controls for API keys on its AI Gateway, addressing the challenge of forecasting and governing AI costs as token-heavy workflows — such as coding agents — become more common. Teams can now set a dollar limit on any API key; once that limit is exceeded, the gateway rejects further requests on that key until the budget resets or is manually increased. The cap covers all AI Gateway providers and models routed through the key, consolidating cost governance in one place.
Budgets can be configured through the AI Gateway API Keys page in the Vercel Dashboard by creating a new key or editing an existing one via the `...` menu and `Edit Key`.
Budgets can be configured through the AI Gateway API Keys page in the Vercel Dashboard by creating a new key or editing an existing one via the `...` menu and `Edit Key`. They can also be created programmatically via the Vercel CLI, with an optional refresh period of `daily`, `weekly`, `monthly`, or `none` to scope the limit to a time window — each period resets at the start of its window in UTC. Keys created via the CLI appear in the team's AI Gateway API Keys view alongside dashboard-created keys. The announcement specifically calls out autonomous workflows that can loop or fan out without supervision, demos and prototypes exposed to unexpected traffic, and developers experimenting without a clear sense of per-model cost as primary use cases for the feature.
Key facts
- 01Teams can set a dollar-denominated spend cap on any AI Gateway API key.
- 02Requests on a key are automatically rejected once its budget limit is exceeded.
- 03Spend caps apply across all AI Gateway providers and models running through the key.
- 04Refresh periods can be set to `daily`, `weekly`, `monthly`, or `none`; each period resets at the start of its window in UTC.
- 05Budgets can be created and managed via both the Vercel Dashboard and the Vercel CLI.
- 06Keys created programmatically via the CLI also appear in the team's AI Gateway API Keys view.
Topics
Summary and scoring are generated automatically from the original article. We always link back to the publisher and never republish images or paywalled content. Last processed Jun 10, 2026 · 15:34 UTC. How this works →