# Set per-user budgets on AI Gateway

Source: [Vercel](https://vercel.com/changelog/set-per-user-budgets-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/set-per-user-budgets-on-ai-gateway-0e7g019  
Published: 2026-08-31T06:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

AI Gateway can now cap each user's aggregate spend across attributed API keys and app tokens, giving unattended coding agents a hard cost boundary.

## Source Summary

AI Gateway now supports **per-user dollar limits** across attributed API keys and app tokens. Requests are rejected at the limit; resets can be daily, weekly, monthly, or disabled, with alerts at **50%, 75%, and 100%**.

## Practical Implication

Set a default allowance for every user, then override it for heavy agent users. Production or shared keys should be attributed to the team, and CLI management requires **Vercel CLI 59.6.2+**.

## Agent-Ready Context

AI Gateway now supports **per-user dollar limits** across attributed API keys and app tokens. Requests are rejected at the limit; resets can be daily, weekly, monthly, or disabled, with alerts at **50%, 75%, and 100%**.

Set a default allowance for every user, then override it for heavy agent users. Production or shared keys should be attributed to the team, and CLI management requires **Vercel CLI 59.6.2+**.

User limits stack with API-key, project, and team budgets, so any applicable cap can block a request. BYOK spend is excluded, and older keys remain team-attributed unless rotated.

## Connected Context

Feed7 judgment across 655 accumulated Signals:

Per-user limits turn shared gateway budgeting into an enforceable allocation mechanism for individual agent users, with configurable resets and threshold alerts. This narrows cost governance from team or project totals to attributed usage, but its stacked caps can reject requests unexpectedly unless operators model every applicable limit. BYOK exclusion and legacy team attribution leave important spend outside this control.

- [Set up coding agents in one command with AI Gateway](https://feed7.dev/p/set-up-coding-agents-in-one-command-with-ai-gateway-0wmcqce) — The shared gateway setup supplies the multi-client control plane; per-user budgets add the explicit limits and attribution policy that the setup alone leaves for teams to define.
- [AI Gateway adds unified fast mode support](https://feed7.dev/p/ai-gateway-adds-unified-fast-mode-support-144dq26) — Because fast tiers usually cost more, per-user caps provide an enforcement consequence for latency-routing choices instead of relying only on policy or metadata inspection.
- [MiniMax M3 and M2.7 are free on AI Gateway](https://feed7.dev/p/minimax-m3-and-m2-7-are-free-on-ai-gateway-185wejm) — The exclusion of BYOK and the possibility of billed fallback show that per-user budgets cover only qualifying gateway spend, so promotion and fallback policy must still be managed separately.

## Context Map

- Layer: infra
- Domains: coding
- Topics: gateways, coding-agents

## Uncertainty

- User limits stack with API-key, project, and team budgets, so any applicable cap can block a request. BYOK spend is excluded, and older keys remain team-attributed unless rotated.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.