Mixedbread

Rate Limiting

Quick Overview

Each endpoint has its own rate limits based on requests per minute, tokens per minute, and requests per day. Exceeding these limits may result in request throttling or rejection. If you need higher limits, please .

Rate Limit Tiers

We offer five tiers with increasing limits. Here's a breakdown for the Embeddings & Reranking endpoint:

TierRequests/MinTokens/MinRequests/DayBurst
Home Baker (Free)100100,0005,00010
Professional Baker300500,000-30
Bakery Shop5001,000,000-50
Bakery Chain1,0005,000,000-100
Bakery Franchise2,00010,000,000-200

Custom tiers are available upon request.

Handling Rate Limits

When you hit a rate limit:

  1. You'll receive a 429 Too Many Requests response
  2. The response will include a Retry-After header
  3. Wait for the specified time before retrying

Example error response:

{
    "type": "too_many_requests_error",
    "url": "https://www.mixedbread.ai/api-reference",
    "message": "Rate limit exceeded. Please try again later.",
    "details": {
        "retry_after": 60,
        "limit": "100",
        "remaining": "0",
        "reset": "1630000000",
        "tier": "1"
    }
}

Best Practices

To optimize your API usage and avoid rate limits, implement exponential backoff in your client code (if not using an SDK), cache results when possible to reduce API calls, and optimize your requests to use fewer tokens.

Need Higher Limits?

If you need higher limits:

  1. or
  2. Provide details about your use case and expected request volume
  3. We'll review and adjust your limits if feasible

Remember, we're here to help you succeed. Don't hesitate to reach out if you have any questions or need assistance optimizing your API usage!

Authentication
Authenticate securely with Mixedbread API using API keys. This guide covers key creation, implementation in requests and SDKs, and key management best practices.
Pagination
Understanding cursor-based pagination across Mixedbread API endpoints. Learn how to navigate through large result sets efficiently using cursors, handle pagination parameters, and implement robust pagination logic.

Last updated: July 28, 2025