$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 Europe v1 · STS · multilingual (8 languages), Multilingual E5 Large Instruct scores 77.4 vs 77.6 — about the same. It is 0% more expensive.
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), Qwen 3 Embedding 8B (better), Jina Embeddings v5 Text Small (open weights).