Research-only embeddings models
13 in the catalogue today. Every one with what it costs, who sells it and where it stands.
Models that turn text into a vector so it can be searched by meaning rather than by words. They are cheap — usually cents per million tokens, and often priced for input only, since nothing comes back but numbers. Two things decide the choice: the dimension of the vector, which sets what your database will cost to hold, and whether the model was trained for your language. Changing model later means re-embedding everything you have.
Weights published for research and explicitly not for selling. They are here because they exist, are often excellent, and are worth knowing about — and because the cheapest way to learn this is not after you have shipped. If a model on this list is what you want, the maker will usually license it commercially on request; that is a conversation, not a download.
- CONCHAI for Pathology Image Analysis Lab @ HMS / BWH
- NV-Embed-v2NVIDIA
- SFR-Embedding-2_RSalesforce30th of 183
- SFR-Embedding-MistralSalesforce14th of 238
- UNIAI for Pathology Image Analysis Lab @ HMS / BWH
- UNI2-hAI for Pathology Image Analysis Lab @ HMS / BWH
- Virchow2paige-ai
- jina-embeddings-v3Jina AI
- jina-embeddings-v4Jina AI$0.05per Mtok in1 selling
- jina-embeddings-v5-omni-nanoJina AI21st of 183· 2 boards$0.05per Mtok in1 selling
- jina-embeddings-v5-omni-smallJina AI15th of 183· 2 boards$0.05per Mtok in1 selling
- jina-embeddings-v5-text-nanoJina AI22nd of 183· 2 boards$0.05per Mtok in1 selling
- jina-embeddings-v5-text-smallJina AI16th of 183· 2 boards$0.05per Mtok in1 selling