Rate Limits & Usage Tiers

Usage tiers determine your rate limits and access to beta features based on your cumulative API spending. As you spend more on API credits over time, you automatically advance to higher tiers with increased rate limits. Higher tiers unlock significantly more requests per minute, and once you reach a tier, you keep it permanently with no downgrade.

Router API requests are rate limited. When a request is rate limited, or an upstream model is overloaded, the API returns a 429 with a Retry-After header — retry after the indicated interval.

The standard Agent API request-count limit applies per API organization. Requests to the Responses API share this limit across models and API keys in the organization. There is no separate per-model requests-per-minute limit.

The limit uses a rolling one-second window. Each accepted request counts against the organization's shared Responses limit for one second, regardless of the model selected.

The Search API has separate rate limits that apply to all usage tiers:

Search Rate Limiter Behavior:

• Single-query request: Consumes 1 query unit
• Multi-query request: Consumes 1 query unit for each query in the array
• Burst: Can consume 50 query units instantly
• Sustained: 50 query units per second on average

The Embeddings API uses tier-based rate limits that scale with your usage tier. Limits are higher than other APIs because each request is a single forward pass on an elastic backend.

Contextualized embeddings have separate, higher limits (5× the standard embeddings tiers):

Rate limiter behavior differs by API; one algorithm does not apply across the platform. Refer to each API section above for the applicable limits.

Agent API requests use a rolling one-second window rather than continuous token refill. When the window is empty, requests can arrive together up to your tier's QPS limit. Additional requests are rejected until earlier requests become more than one second old and leave the window.

For example, an organization with a 33 QPS limit can make up to 33 Agent API requests in any rolling one-second period.

When you exceed your rate limits:

1. 429 Error - Your request gets rejected with "Too Many Requests"
2. Recovery Timing - Capacity returns according to the applicable API's limiter. For the Agent API, each accepted request leaves the rolling window after one second.