[API reference]

Rate limits

Limits are set per team and shared by every key on it. They scale with your plan and are reported on every response.

Limits by plan

Plan	Requests / min	Tokens / min	Streams	Images / min
Pay as you go	60	200k	10	20
Builder	600	2M	50	100
Max	3,000	10M	200	500
Enterprise	Custom	Custom	Custom	Custom

Streams are concurrent open streaming responses.

Rate limit headers

Header	Description
`x-ratelimit-limit-requests`	Requests allowed per minute.
`x-ratelimit-remaining-requests`	Requests left in the current window.
`x-ratelimit-reset-requests`	Time until the request window resets, such as `1.7s`.
`x-ratelimit-limit-tokens`	Tokens allowed per minute.
`x-ratelimit-remaining-tokens`	Tokens left in the current window.
`retry-after`	Seconds to wait. Sent only with `429`.

response headers

http

HTTP/2 200x-topo-request-id: req_7Hq2kf91x-ratelimit-limit-requests: 600x-ratelimit-remaining-requests: 583x-ratelimit-reset-requests: 1.7sx-ratelimit-limit-tokens: 2000000x-ratelimit-remaining-tokens: 1942310

Staying under the limit

Batch embeddings: one request can carry 2,048 inputs.
Set max_tokens. Token limits count the requested maximum until the response finishes.
Give each agent its own key with a spend limit, so one runaway loop cannot starve the rest of the team.
Priority routing on Builder and Max shortens queues at peak, but does not raise the limits.