skip to content
gigarouter gigarouter
models / reranker · coming soon

mxbai-rerank-xsmall-v1

mixedbread-ai/mxbai-rerank-xsmall-v1

A popular open reranker model, with 551K downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.

est. price
~$0.008
/ 1k docs · estimated, set at launch
API providers
0
downloads / mo
551K
license
apache-2.0

about this model

mixedbread-ai/mxbai-rerank-xsmall-v1 is a reranking model hosted by gigarouter. Its purpose is to reorder a set of candidate documents or passages by relevance to a given query. As an xsmall variant, it is optimized for efficient inference, making it suitable for latency-sensitive applications where a lightweight reranker is required. The model card does not provide specific benchmark numbers, performance comparisons, or detailed strengths beyond the model’s architecture and scale. It is available as a managed, OpenAI-compatible API through gigarouter, eliminating the need for local installation.

not yet live

We're benchmarking and onboarding mxbai-rerank-xsmall-v1 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.