Batas rate memastikan penggunaan yang adil dan stabilitas sistem. Batas bervariasi menurut paket.
Your account supports up to the concurrent jobs shown for your current tier. Some high-demand models may be queued when model-specific capacity is full.
<= $10 = 10 jobs, $100 = 20, $500 = 30, and $1,000+ = 40.
Need higher limits? Contact sales at sales@renderful.ai.
| Credits Purchased | Concurrent Jobs |
|---|---|
| <= $10 | 10 |
| $100 | 20 |
| $500 | 30 |
| $1,000+ | 40 |
Separately from concurrency, each API key has a per-minute request budget. Reads and writes are metered independently, so polling job status never consumes the budget you need to submit new jobs.
GET /v1/generations/{id} and other GET endpoints) — 600 requests per minute by default.A throttled request returns 429 with a Retry-After header and a scope field of read or write telling you which budget was exhausted. Honor Retry-After rather than retrying immediately.
Account concurrency is global, but some providers and high-demand models have tighter internal capacity limits. Those requests are accepted and queued instead of being rejected when the model-specific pool is full.