NV-Embed-v2
the leaderboard model you are not allowed to ship
strong retrieval scores and an explicit ban on commercial use — ranked last because it is listed as a production option almost everywhere and it is not one.
on the numbers NV-Embed-v2 is a serious model: 8 billion parameters, 4,096 dimensions, 32,768 tokens of context, and a 72.31 average across 56 MTEB tasks that took the top of the english leaderboard when it landed in 2024. if benchmark position were the only criterion it would rank near the top of this page.
it carries CC-BY-NC-4.0, and NVIDIA's model card does not leave it to inference: this model should not be used for any commercial purpose. commercial users are pointed at NeMo Retriever NIM microservices, which are a separate product under separate licensing. that is not an ambiguity to interpret in your favour — it is a sentence.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- embedding models
- pricing
- free — non-commercial use only
- website
- huggingface.co
strong retrieval scores and an explicit ban on commercial use — ranked last because it is listed as a production option almost everywhere and it is not one.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.
more embedding models
text-embedding-3-small
openai's cheaper embedding model, shortenable to fewer dimensions
multilingual-e5
microsoft's open multilingual embedding family, widely used as a baseline