Rate Limits
Rate limits are measured across five key dimensions:Requests per minute (RPM)
: The maximum number of API requests you can send within one minute.Tokens per minute (TPM)
: The maximum number of tokens (input) you can use within one minute.Requests per day (RPD)
: The maximum number of API requests you can send within one day.Tokens per day (TPD)
: The maximum number of tokens (both input and output) you can use within one day.Monthly Token Limit
: The maximum total tokens (both input and output) you can use within one calendar month.
Cost per 1K Tokens is calculated as , equivalent to
Tier | RPM | TPD | TPM | Monthly Token Limit |
---|---|---|---|---|
Free | 5 | 3,000 | 2,000 | 10,000 (Est.) |
Basic | 30 | 10,000 | 10,000 | 66,667 (Est.) |
Standard | 100 | 40,000 | 100,000 | 400,000 (Est.) |
Pro | 400 | 100,000 | 200,000 | 1,000,000 (Est.) |
Enterprise | Custom | Custom | Custom | Custom |
Response Headers
Every API response includes usage information within the_metadata
field. This allows you to track your current consumption against your plan limits directly from your application.
Rate Limit Errors
When your API usage exceeds the allocated rate limit for your plan, the API will return an HTTP Status Code429: Too Many Requests
. The response body will include details about the exceeded limit and when it will reset.