Skip to main content

​
Rate Limit Overview

API requests are rate limited to ensure fair usage and system stability. Limits are enforced at two levels: per IP address and per user account.

​
Current Limits

DimensionLimit
Per IP address60 requests / minute
Per user account600 requests / minute
When either limit is exceeded, the API returns HTTP status 429 Too Many Requests. Limits may vary based on your plan — contact support for higher limits.

​
Rate Limit Exceeded Response

When a rate limit is exceeded, the API responds with: 
{
  "success": false,
  "message": "Rate limit exceeded. Please retry later.",
  "error_code": "RATE_LIMIT_EXCEEDED"
}

​
Handling Rate Limits

​
Implement Exponential Backoff

async function apiRequestWithBackoff(url, options, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    const response = await fetch(url, options);

    if (response.status === 429) {
      const waitTime = Math.pow(2, i) * 1000;
      console.log(`Rate limited. Retrying in ${waitTime}ms...`);
      await sleep(waitTime);
      continue;
    }

    return response;
  }

  throw new Error('Max retries exceeded due to rate limiting');
}

​
Best Practices

  • Implement exponential backoff with jitter for retries
  • Cache responses when possible to reduce redundant requests
  • Batch operations where supported (e.g. batch document removal)
  • Implement client-side request queuing to smooth out traffic spikes
  • Monitor request volume and log 429 responses for observability

​
Storage Quotas

ResourceLimit
Total storage100 GB (varies by plan)
Max file size500 MB
ProjectsUnlimited
Memories per projectUnlimited
API keys per project10

​
Requesting Higher Limits

To request higher rate limits, contact support with:
  • Current usage patterns and peak request volume
  • Expected future usage
  • Use case description

​
Next Steps

API Overview

Return to API overview

Error Handling

Handle rate limit errors