View as /docs.md
Reference

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

TierRPMNotes
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)20,000Auto-promoted on first top-up. Cost + a 5% platform fee on every call.
EnterpriseCustomCustom 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:

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.