$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 JMTEB v2 · STS · Japanese, E5 Mistral 7B Instruct scores 83.6 vs 83.9 — about the same.
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.
EmbeddingGemma 300M (cheaper), Ja Embed Sts (open weights).