Reranking
What is Reranking?
Reranking takes initial search results and sorts them based on how closely they match the real meaning behind a user's query. This helps ensure that the most useful information appears first. It also lets you pass only the best and most relevant results to the LLM, keeping the context concise and meaningful.
Rerank your first documents
Try out the example to understand how reranking can improve your search results.
Available Reranking Models
Choose the right reranking model for your use case:
| Model Card | Description |
|---|---|
| mxbai-rerank-xsmall-v1 | Most compact reranking model for semantic search. Delivers good performance with minimal resource requirements. |
| mxbai-rerank-base-v1 | Balanced size and performance for boosting search relevance. Easily integrates into existing keyword-based search systems. |
| mxbai-rerank-large-v1 | Flagship model for high-accuracy semantic reranking. Excels at complex and domain-specific queries. |
| mxbai-rerank-base-v2 | State-of-the-art, multilingual reranking with reinforcement learning. Handles long contexts and diverse use cases. |
| mxbai-rerank-large-v2 | Flagship second-generation model with best-in-class accuracy and speed. Excels at long contexts, complex queries, and multilingual tasks. |
Check out the API Reference for more information.
Embeddings
Leverage Mixedbread's Embeddings API to access state-of-the-art models for vector generation.
Account
All information about accounts.
Last updated: July 12, 2025