Cloudflare AI Gateway now supports spend limits

Cloudflare has introduced spend limits for its AI Gateway, allowing users to set cost-based budgets that block further requests with a 429 response when cumulative spending reaches a defined threshold within a time window. The feature tracks actual dollar costs per request based on model pricing and can be scoped by model, provider, or custom metadata dimensions like user ID or team. This gives organizations real-time cost control over AI API usage, with options to block requests or automatically fall back to cheaper models when budgets are exceeded.

Spend limits Spend limits let you set cost-based budgets on your AI Gateway. When cumulative spend reaches the limit within a time window, AI Gateway blocks further requests with a 429 response until the window resets. Unlike rate limiting /ai-gateway/features/rate-limiting/ , which caps the number of requests, spend limits track actual dollar cost per request based on model pricing. You can scope limits to any combination of model, provider, or custom metadata /ai-gateway/observability/custom-metadata/ dimensions like user ID, team, or application. Spend limits apply to both Unified Billing /ai-gateway/features/unified-billing/ requests and BYOK /ai-gateway/configuration/bring-your-own-keys/ requests for models with known pricing. Each spend limit rule defines a budget in dollars over a rolling or fixed time window. AI Gateway calculates the cost of each request based on token usage and model pricing, then tracks cumulative spend against the limit in real time. Before sending a request to the provider, AI Gateway evaluates all applicable spend limit rules at once. If any individual rule is over budget, the request is blocked with a 429 response. Spend limits are eventually consistent. The current request's cost is recorded after completion, so a burst of concurrent requests can briefly exceed the limit before enforcement catches up. Each rule can be scoped by model, provider, or custom metadata dimensions. Each dimension can be configured in one of two modes: | Mode | Behavior | Example | |---|---|---| Split by value | Each distinct value gets its own independent budget bucket. | Splitting by metadata.user id gives every user their own budget. | Filter by value | The rule applies only when the dimension equals a specific value. | Filtering metadata.team to engineering limits only requests from the engineering team. | If a dimension is not configured on a rule, all values share one budget bucket. For example, a rule without a provider dimension tracks spend across all providers together. Given a request with model=openai/gpt-5.5 and metadata.user id=u 42 : | Scenario | Dimensions | Budget bucket | |---|---|---| | Global budget for everyone | None | One shared bucket | | Per-user budget | metadata.user id : split by value | Separate bucket per user | | Per-provider, per-user | metadata.user id : split by value, provider : split by value | Separate bucket per user+provider combination | | Specific model only | model : filter by value openai/gpt-5.5 | Only applies to openai/gpt-5.5 requests | | Per-user, per-model | metadata.user id : split by value, model : split by value | Separate bucket per user+model combination | Spend limits are configured on the gateway via the dashboard or the API. You can define up to 20 rules per gateway. To scope spend limits by custom dimensions like user ID or team, attach custom metadata /ai-gateway/observability/custom-metadata/ to your requests. When a spend limit is exceeded, AI Gateway returns a 429 Too Many Requests response. You have two options: Block requests default - The request is rejected until the budget window resets. Fall back to a cheaper model - Create a Dynamic Route /ai-gateway/features/dynamic-routing/ with a primary model and a fallback for example, anthropic/claude-opus-4.7 with a fallback to @cf/moonshotai/kimi-k2.6 . Then set a spend limit on the primary model using this feature. When the primary model's budget is exceeded, AI Gateway automatically routes requests to the fallback model instead of blocking them. You can track your spend per model, provider, or any custom metadata attribute on the Analytics dashboard /ai-gateway/observability/analytics/ . Use this to understand usage patterns and set informed budgets. - Cost tracking is a best-effort estimation based on token counts and model pricing. Refer to your provider's dashboard for exact billing amounts. - A maximum of 20 spend limit rules can be configured per gateway.