Rate Limits

Request Rate Limits

Subscriber requests are limited to 120 requests/min per account. Requests exceeding the rate limit receive a 429 response with a Retry-After: 60 header — wait and retry.

AI Usage Budget

The only LLM-backed tool is generate_smart_program. Each subscription includes a monthly AI usage allowance — a spend cap on LLM usage, not a fixed call count; it resets each billing cycle and is shown as a percentage in the app settings. Exceeding it returns a rateLimited response.