There is no per-unit API price: self-host only.
There is no free API. The weights are open, so you can run it yourself.
#49 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Russian v1.1 · STS · Russian, Gte Qwen1.5 7B Instruct scores 71.3 vs 71.7 — about the same.
Released 2024-04-20. It is the current version in its line.
Yes, the weights are open (Apache-2.0 licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Gte Qwen1.5 7B Instruct is an open-weights embeddings & retrieval model from Alibaba (Qwen), released Apr 2024.
EmbeddingGemma 300M (better), Qwen 3 Embedding 8B (open weights).