Rate Limits
Rate limits depend on your account level, which is unlocked automatically based on your lifetime spend on the platform.
Tchavi is pay-as-you-go: credits are the natural gate, and there is no subscription. Rate limits depend on your account level, which is unlocked automatically based on your lifetime spend on the platform. Two independent limits apply per user per minute:
- RPM — maximum number of requests per minute.
- TPM — maximum tokens processed per minute (input + output). For TTS, each character counts as 1 token. For Whisper, each billed minute counts as 1,000 tokens.
Account levels
| Account level | Unlocked at | RPM | TPM | Max API keys |
|---|---|---|---|---|
| Free | Default | 10 req/min | 100,000 | 1 |
| Builder | First top-up | 30 req/min | 500,000 | 3 |
| Growth | 10,000 FCFA lifetime | 120 req/min | 1,000,000 | 10 |
| Pro | 50,000 FCFA lifetime | 300 req/min | 3,000,000 | Unlimited |
A global IP-based limit of 500 req/min also applies across all users sharing the same IP address.
The Free level
Every account starts on Free and stays there until its first top-up. Two extra restrictions apply on that level only:
- Budget-group models only. Calling any other model returns
403 plan_model_restricted. - 50 requests per day, reset at midnight UTC. Beyond that you receive
429 free_tier_daily_limitwith aRetry-Afterheader.
Any top-up — 1 000 FCFA is enough — moves the account to Builder and lifts both restrictions.
Exceeding a limit
When a limit is exceeded you receive a 429 response with a Retry-After header indicating how many seconds to wait before retrying. Your current level, RPM budget, and TPM budget are always visible in the X-RateLimit-* response headers (see Credits & Billing).