Rate limits protect platform stability and ensure fair usage.
Limits by Tier
| Tier | RPM | TPM | Notes |
|---|---|---|---|
| Welcome / Free | 10 | 40,000 | Starter models only |
| Pay-as-you-go | 60 | 400,000 | After first purchase |
| High usage | 200+ | 2M+ | Contact support |
RPM = requests per minute
TPM = tokens per minute (input + output)
Per-Key Limits
Configure in Dashboard → API Keys → Key Settings:
- Custom RPM cap (below account limit)
- Per-key spend limit (USD)
Free Model Limits
Free-tier models (:free suffix where available):
- 10 requests/day without purchase
- 100 requests/day with purchased credits
Not suitable for production.
Response Headers
x-ratelimit-limit-requests: 60
x-ratelimit-remaining-requests: 45
x-ratelimit-reset-requests: 30s
x-ratelimit-limit-tokens: 400000
x-ratelimit-remaining-tokens: 350000
429 Too Many Requests
{
"error": {
"message": "Rate limit exceeded",
"type": "rate_limit_error",
"code": "rate_limit_exceeded"
}
}
Retry Strategy
import time
import random
def retry_with_backoff(func, max_retries=5):
for attempt in range(max_retries):
try:
return func()
except RateLimitError:
wait = min(60, (2 ** attempt) + random.random())
time.sleep(wait)
raise
Increasing Limits
Email support@boundlessapi.com with:
- Account email
- Use case description
- Expected RPM/TPM
- Current monthly spend
Enterprise: custom limits in contract.