ai-toolfinder
ENDE
Submit a tool

mxbai-rerank v2 overview and key facts (October 2026)

Open reranker models from Mixedbread under Apache 2.0 for more than 100 languages and code, also available through the vendor's search API.

AI modelRAG & Document ParsingRerankersEmbedding modelsSearch APIs
Free

from $20 per month

Visit website Write a review
Visit website

What is mxbai-rerank v2?

mxbai-rerank v2 is a pair of open reranker models, large and base, that sort search results by relevance to a query. Developers can self-host them or use them through Mixedbread's hosted search API.

Mixedbread AI Inc. publishes the models on Hugging Face under the Apache 2.0 license. The model card lists support for more than 100 languages with strong English and Chinese performance, code understanding and long-context support; training combined reinforcement learning with contrastive and preference learning. As of September 28, 2026 the large model had about 89,000 downloads in the last month and the base model about 29,000. Mixedbread also runs a hosted search product with rerank as a paid add-on. Its privacy policy states SOC 2 Type II certification for the Security criterion, and a data processing agreement is published on its website.

mxbai-rerank v2 AI features and use cases

  • Reranks results for RAGThe model scores each candidate passage against the query and reorders the list before it reaches the language model. Answers then rely on the most relevant text.
  • Ranks code and technical contentCode understanding is listed among the model's capabilities. Developer portals and internal engineering wikis can use one reranker for prose and code.
  • Adds reranking to hosted searchIn Mixedbread's search API, rerank is an optional add-on to semantic search. Teams without their own GPU servers get reranking without running the model.

What sets mxbai-rerank v2 apart

  • Two sizes allow a trade-off between accuracy and speed on your own hardware.
  • Apache 2.0 weights plus an optional hosted API with published per-query prices.
  • Enterprise customers can keep data in their own bucket or cloud (BYOB, BYOC).

Where mxbai-rerank v2 is strongest

United States Available internationally

The publisher is Mixedbread AI Inc., which according to its privacy policy stores data mainly in the United States.

Questions to ask before you buy mxbai-rerank v2

Self-hosting needs GPU capacity for the large model. For the hosted API, the privacy policy states that data is stored mainly in the US and that free-tier data is retained indefinitely, so use a paid plan for business data and review the DPA. SSO is part of the enterprise plan.

mxbai-rerank v2 reviews

No reviews yet. Be the first to share how your team uses it.

Every review shows its verification level. We read each one before it goes live. How we check reviews

Questions about mxbai-rerank v2

Are the mxbai-rerank v2 models free?

Yes, the weights are published under Apache 2.0. The hosted search API is paid after a $5 starter credit.

Which languages are supported?

The model card lists more than 100 languages, with strong performance in English and Chinese, plus code.

Where does the hosted API store data?

According to Mixedbread's privacy policy, mainly on servers in the United States, with some service providers such as analytics in the EU.

mxbai-rerank v2 update historyno updates yet

No changes recorded for mxbai-rerank v2 yet.

Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.

Alternatives to mxbai-rerank v2

Tools in the same category (Rerankers) with the most overlapping markets.

All 7 alternatives →
From $0.02 usage-based · Free plan🇺🇸

MongoDB's embedding and reranker API with general, multilingual and domain models for finance, legal and code.

embedding APIsrerankers
Usage-based · Free plan🇨🇦

Embedding model from Canadian vendor Cohere for text and images in 100+ languages, via API, dedicated or private deployment.

embedding APIsrerankersenterprise search
From $3,250 per month · Free trial🇨🇦

Reranking API from Toronto-based Cohere that reorders search results by semantic relevance, multilingual and also for JSON.

rerankerssearch APIsfast & low-cost models

Compare mxbai-rerank v2 with these alternatives →