Documentation

Rate limits

Limits depend on your workspace's plan and apply per API key on a fixed window. The official SDKs read the headers below and back off automatically.

Per-plan limits

Freemium — 50 requests per day.
Pro / Team — 60 requests per minute.

Headers on every response

X-RateLimit-Limit — requests allowed per window.
X-RateLimit-Remaining — requests remaining in the current window.
X-RateLimit-Reset — unix-seconds timestamp when the window rolls over.

When you're over

You'll see a 429 Too Many Requests with a Retry-After header (in seconds) and the standard error body. On freemium, the body includes tier and upgrade_url so consumer UIs can surface the upgrade path:

{
  "error": {
    "type": "rate_limited",
    "message": "Free tier allows 50 requests/day. Upgrade to Pro for 60 requests/minute.",
    "tier": "free_tier",
    "upgrade_url": "https://klang.ai/upgrade"
  }
}

Sleep until Retry-After elapses, then continue. The SDKs do this for you.

Need a higher limit?

Contact support with your workspace id and a sketch of the traffic pattern you expect. Most increases are turned around the same day.