Mixedbread AI
About Mixedbread AI
Mixedbread develops search tools and embedding or reranking models. Its documentation distinguishes earlier standalone model releases from current managed-search workflows. Embeddings represent content, while reranking reorders candidates after an initial retrieval step.
Focus
- Search infrastructure
- Embedding models
- Reranking models
Projects and interfaces
mxbai embedding and reranking releases
model families
Published model families with maintained references in Mixedbread's legacy-model documentation.
Stores search and reranking
search service
Managed-search workflows described separately from the earlier standalone model interfaces.
Scope and limitations
- Earlier direct APIs and model releases have different lifecycle conditions from the current managed-search service.
Official references
- Mixedbread model-release references. Checked .
- Mixedbread reranking documentation. Checked .
Models
5 named catalog records. These are name and distribution records, not a count of distinct model architectures.
- mxbai-embed-large
- mxbai-embed-large:335m
- mxbai-embed-large:335m-v1-fp16
- mxbai-embed-large:latest
- mxbai-embed-large:v1
Model families
- Mixedbread (catalog grouping)
- mxbai-embed-large