$0.05 per 1M tokens.
There is no free API; it costs $0.05 per 1M tokens. The weights are open, so you can run it yourself.
#21 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Indic v1 · STS · multilingual (13 languages), Jina Embeddings v5 Text Small scores 47.8 vs 47.8 — about the same. It is 0% more expensive.
Released 2026-02-17. It is the current version in its line.
Yes, the weights are open (cc-by-nc-4.0 licence).
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Jina Embeddings v5 Text Small is an open-weights embeddings & retrieval model from Jina AI, released Feb 2026.
Qwen 3 Embedding 8B (cheaper), STS Multilingual Mpnet Base v2 (open weights).
CheaperQwen 3 Embedding 8BunstatedOpen+29%-80%$0.01Memory (4-bit): 0.4 GB → 4.5 GBGOpenSTS Multilingual Mpnet Base v2unstated+77%——Max input: 33K tokens → 0K tokens
CheaperBge M3unstatedOpen+9%-80%$0.01Max input: 33K tokens → 8K tokens
Text Multilingual Embedding 002unstated+12%—$0.025Max input: 33K tokens → 2K tokens
KaLM Embedding Gemma3 12B 2511Open+33%——Memory (4-bit): 0.4 GB → 7.1 GBOOcten Embedding 8BOpen+29%——Memory (4-bit): 0.4 GB → 4.5 GBLQwen Indic v1Open+29%——Memory (4-bit): 0.4 GB → 4.5 GB