Rate Limits

Utopian Labs implements rate limiting to ensure fair usage of our API resources. Understanding these limits will help you better plan your API integration.

Default Rate Limits

By default, your API account includes the following limits:

1,000 new agent runs per day across all agents
100 model predictions per minute for the 'reply intent light' model

Need higher limits? Talk to sales about our enterprise plans with increased rate limits.

Rate Limit Responses

When you exceed your rate limits, the API will respond with appropriate status codes:

429 Too Many Requests: You've exceeded your rate limit
402 Payment Required: Your account has defaulted on payments, resulting in a rate limit of 0

Rate Limit Response Examples

curl https://api.utopianlabs.ai/v1/endpoint \
  -H "Authorization: Bearer your_api_key_here"

# Response when rate limited:
# HTTP/1.1 429 Too Many Requests
# {
#   "error": "Rate limit exceeded"
# }