$0.022 per 1M tokens.
There is no free API; it costs $0.022 per 1M tokens. The weights are open, so you can run it yourself.
#41 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Scandinavian v1 · Retrieval · multilingual (3 languages), E5 Mistral 7B Instruct scores 61.9 vs 62 — about the same. It is 81% cheaper.
Released 2024-02-08. It is the current version in its line.
Yes, the weights are open (MIT licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
E5 Mistral 7B Instruct is an open-weights embeddings & retrieval model from intfloat, released Feb 2024.
Qwen 3 Embedding 4B (cheaper), Multilingual E5 Large (better), F2LLM v2 14B (open weights).