Skip to main content
The API enforces a default request-rate limit, sized for typical production load. Exceed it and the call returns 429 Too Many Requests with the standard error envelope: 
{ "code": "RATE_LIMITED", "message": "Rate limit exceeded: ..." }
429 responses do not currently carry rate-limit headers, so do not branch on Retry-After or X-RateLimit-*. Treat a 429 as the signal to slow down, and retry with backoff.

​
Backoff

Retry on 429 with exponential backoff plus jitter. Pseudocode: 
import random, time

delay = 1
for attempt in range(5):
    response = call_runflow()
    if response.status != 429:
        break
    time.sleep(min(delay, 32) + random.uniform(0, 1))
    delay = min(delay * 2, 32)

​
Run capacity

Runs are dispatched asynchronously onto a shared worker fleet. When capacity is busy, a run waits in the queued status until a worker is free rather than being rejected, so a sustained backlog shows up as runs sitting in queued (see Runs for the lifecycle). If queue times grow beyond what your workload can tolerate, get in touch about higher throughput.

​
Need a higher limit?

Talk to us. Include peak QPS, average payload size, and target concurrency.

Errors

All status codes including 429.

Pricing

Per-request and per-second pricing.