Skip to main content
ARouter enforces rate limits to ensure fair access and protect service availability. Making additional accounts or API keys does not increase your rate limits — capacity is governed globally per account.

Checking Your Current Limits

To check the rate limit or credits remaining on an API key, make a GET request to /v1/key:
import requests

response = requests.get(
    "https://api.arouter.ai/v1/key",
    headers={"Authorization": f"Bearer {AROUTER_API_KEY}"}
)
print(response.json())
A valid API key returns:
{
  "data": {
    "label": "my-key",
    "limit": 100.0,
    "limit_reset": "monthly",
    "limit_remaining": 72.45,
    "usage": 27.55,
    "usage_daily": 2.10,
    "usage_weekly": 8.40,
    "usage_monthly": 27.55,
    "is_free_tier": false
  }
}
FieldDescription
limitCredit limit for this key (null = unlimited)
limit_resetWhen the limit resets (daily, weekly, monthly, or null)
limit_remainingCredits remaining before the key is blocked
usageAll-time credits consumed
usage_daily / _weekly / _monthlyUsage for the current UTC period
is_free_tierWhether the account has purchased credits before

Free Tier Limits

Models with IDs ending in :free are available without purchasing credits, subject to these limits:
ConditionRPMRPD
No paid credits purchased20 req/min50 req/day
At least $5 in credits purchased20 req/min1,000 req/day
Free tier limits apply to free model variants (:free suffix) only. Paid models require a credit balance.

DDoS Protection

Cloudflare’s DDoS protection automatically blocks requests that dramatically exceed reasonable usage patterns. These blocks are temporary and lift once traffic normalizes.

Negative Balance

If your account has a negative credit balance, you may see 402 Payment Required errors — including on free models. Adding credits to bring your balance above zero restores access.

Per-Key Spending Limits

You can configure spending limits on individual API keys to control costs:
  • Limit: Maximum credits the key can consume
  • Reset interval: daily, weekly, monthly, or never
Set limits when creating or updating a key via the Key Management API.

Model-Specific Limits

Some high-demand models may have additional per-model rate limits independent of your account’s overall quota. If you encounter 429 Too Many Requests errors on a specific model, consider:
  • Using the :floor or :nitro variant to access different provider endpoints
  • Specifying an ordered candidate model list to spread load across models
  • Implementing exponential backoff and retry logic in your client
See Error Handling for retry best practices.