Rate limits
The API takes a given number of calls in a given time. A budget refills steadily, not all at once: a refused call only waits for the next one to come back, and the answer says when.
Budgets a call counts against every budget it falls under
| Name | Budget |
|---|---|
calls | 300 requests per 5 minutes per accountRefills steadily: one back every second. |
writes | 60 write and destructive operations per hour per accountRefills steadily: one back every minute. |
by_ip | 1200 requests per 5 minutes per IP addressRefills steadily: four back every second. |
Check what is left of your budget:
manitu_access_rate_limit_getPOST /v1/access/rate-limit/get.Headers what is left, in the answer
RateLimit-PolicyThe budgets that apply to the request: size, window and name.
RateLimitWhat is left of a budget, and in how many seconds it is full again.
X-RateLimit-LimitHow many calls that budget takes at once when it is full, as older clients read it.
X-RateLimit-RemainingWhat is left of it.
X-RateLimit-ResetIn how many seconds it is full again.
Retry-AfterWith a 429: in how many seconds the next call passes.
Past a budget
REST: the request is refused with 429; Retry-After says in how many seconds the next call passes.
MCP: the tool returns an error (isError: true) with a text the model can read, so an agent can wait and try again instead of giving up.