Docs
Docs pages

API reference

Rate limits and quotas

Limits keep one caller from filling the queue. The backend analyses one video at a time and the others wait.

LimitValueWhen you pass it
Requests per API key10 a minute on Free (fixed one-minute windows); see the plan table below429 rate_limited with Retry-After
Playground calls per account6 a minute429 rate_limited
Free video minutes1,000 a month per account, reset on the 1st (UTC)429 monthly_quota_exceeded
A cap you set on one keyAny number of video minutes a month429 key_cap_exceeded
Video size25 MB413 file_too_large
Video analysed per call120 s (use start_s to walk a longer file)Analysis stops at 120 s
Call duration5 minutes (about 20 s of video per call is safe on the CPU backend)504 inference_timeout
Sign-in attempts10 per 15 minutes per network and per email429 rate_limited

Model calls carry X-RateLimit-Limit, X-RateLimit-Remaining and X-RateLimit-Reset (Unix seconds), and on a capped plan X-Quota-Limit-Minutes and X-Quota-Remaining-Minutes. GET /v1/me returns the same for the calling key. Sample calls (?sample=) count as requests but never as minutes.

By plan

PlanRequests a minute per keyVideo minutes a monthActive keysLogs kept
Free101,000, then calls stop2030 days
Pay as you go60No cap2090 days
Always on120No cap5090 days
Enterprise600No cap20090 days

Billing is not switched on, so every account is on Free today. The paid rows are what the API will enforce when it is.

Versions

The path carries the major version (/v1). Every response also carries a dated Vitals-Version header, currently 2026-11-21. Changes that could break a client get a new date and a line in the changelog.