Rate limits
Limits are per-key, measured in requests per minute, and bound to your tier. Scoped keys can carry a stricter local cap.
Tiers
| Tier | RPM | Notes |
|---|---|---|
| Trial (card on file) | 600 | $1 credit across a curated trial catalog led by GLM-5.2. A saved card is all it takes — no charge until you top up. Without a card on file the API returns 402 card_required. |
| Paid (PAYG) | 20,000 | Auto-promoted on first top-up. Cost + a 5% platform fee on every call. |
| Enterprise | Custom | Custom RPM + SLA + per-region routing + dedicated endpoint — enterprise@aigateway.sh |
Sub-accounts inherit their parent's tier ceiling and can carry a stricter local rate_limit_rpm set at creation.
Response headers
Every successful response carries:
x-ratelimit-limit-requests— your current RPM ceilingx-ratelimit-remaining-requests— requests left this minutex-ratelimit-reset-requests— seconds until the window resets
When you exceed your limit, the gateway returns 429 rate_limit_error with a Retry-After header — back off for that many seconds. The SDKs honor this automatically with exponential jitter on top.
Windows
Limits are counted in a fixed 60-second window — your full RPM is available the moment a new window opens. If you need steadier high throughput — training-data generation, large eval runs — prefer the Batch API, which doesn't count against RPM.
Need more?
Enterprise limits (custom RPM, dedicated capacity, per-region routing) are set in contracts — email enterprise@aigateway.sh.