$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.
#78 of 200 in Embeddings.
On MTEB Russian v1.1 · Multilabel Classification · Russian, Gte Large scores 27.2 vs 27.2 — about the same. It is 0% more expensive.
Through the thenlper API.
Released 2023-07-27. 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.
Gte Large is an open-weights embeddings & retrieval model from thenlper, released Jul 2023.
EmbeddingGemma 300M (cheaper), Giga Embeddings Instruct 10B A1.8B 0826 (open weights).
CheaperEmbeddingGemma 300MunstatedOpen+49%-80%$0.002Languages: not verifiedaOpenGiga Embeddings Instruct 10B A1.8B 0826unstated×2.2——Memory (4-bit): 0.2 GB → 6.3 GBsCheaperAll Mpnet Base v2unstatedOpensame-50%$0.005Max input: 1K tokens → 0K tokenstCheaperGte BaseunstatedOpen-4%-50%$0.005iCheaperE5 Base v2unstatedOpen-4%-50%$0.005
Qwen 3 Embedding 8BunstatedOpen+64%same$0.01Languages: not verified+1iMultilingual E5 Large InstructunstatedOpen+51%same$0.01Memory (4-bit): 0.2 GB → 0.3 GB