Preview docs. Hallucination Guard is the only live endpoint today.

The rest of the API surface ships through the rest of 2026. Join the waitlist to be first in line and shape what we build first.

Read Hallucination Guard reference Join the waitlist

Getting started

Rate limits

Per-tier monthly call budgets plus per-second burst limits. Every response carries the rate-limit headers so your client can adapt without external state.

Tier limits

Tier	Monthly	Burst	Overage
Hobbyist	100 calls	2 req/sec	Hard cap (429 after limit)
Startup	10,000 calls	20 req/sec	$0.02/call
Scale	100,000 calls	100 req/sec	$0.005/call
Enterprise	Custom	Custom	Per contract

Headers on every response

HTTP

HTTP/1.1 200 OK
X-RateLimit-Limit: 10000
X-RateLimit-Remaining: 9847
X-RateLimit-Reset: 1717286400
X-RateLimit-Burst-Limit: 20
X-RateLimit-Burst-Remaining: 18

X-RateLimit-Reset is a Unix timestamp marking when your monthly bucket resets. Burst-Remaining ticks back up over a one-second sliding window.

Handling 429s

When you hit the per-second burst limit you'll get a 429 with Retry-After:

HTTP

HTTP/1.1 429 Too Many Requests
Retry-After: 1
Content-Type: application/json

{ "error": { "type": "rate_limit_exceeded", "scope": "burst" } }

Recommended client behaviour: exponential backoff capped at Retry-After, with jitter. The SDKs do this automatically.

Hitting the monthly cap

Hobbyist: further requests return 429 with scope: "monthly" until reset
Startup / Scale: overage billing kicks in; requests succeed and you're billed at the per-call overage rate
Enterprise: per your contract

Set up monthly-cap alerts in Settings → Notifications to get an email at 50%, 80%, and 95% of your budget.