$0.01 per 1M tokens.
There is no free API; the cheapest paid price is $0.01 per 1M input tokens. The weights are open, so you can run it yourself.
#75 of 200 in Embeddings.
On MTEB Portuguese v1 · Classification · Portuguese, Multilingual E5 Large Instruct scores 64.6 vs 65.5 — about the same. It is 55% cheaper.
Through the intfloat API.
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.
Multilingual E5 Large Instruct is an open-weights embeddings & retrieval model from intfloat, released Feb 2024.
EmbeddingGemma 300M (cheaper), GritLM 7B (better).
CheaperEmbeddingGemma 300MunstatedOpen+3%-80%$0.002Languages: not verifiedGBetterGritLM 7BunstatedOpen+7%——Languages: not verified+1iOpenE5 Mistral 7B Instructunstatedsame+124%$0.022Languages: loses Esperanto, es, Estonian +89+1iOpenE5 Large Matryoshka Sts Pt-5%——Languages: loses en, Esperanto, es +89
OpenQwen 3 Embedding 0.6Bunstated-5%same$0.01Languages: not verified+1