$0.02 per 1M tokens.
There is no free API; it costs $0.02 per 1M tokens. The weights are open, so you can run it yourself.
#32 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
On MTEB Dutch v1 · Multilabel Classification · Dutch, Jina Embeddings v5 Text Nano scores 30.9 vs 30.9 — about the same.
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 Nano is an open-weights embeddings & retrieval model from Jina AI, released Feb 2026.
Qwen 3 Embedding 8B (cheaper), EmbeddingGemma 300M (better), F2LLM v2 8B (open weights).
CheaperQwen 3 Embedding 8BunstatedOpen+34%-50%$0.01Memory (4-bit): 0.1 GB → 4.5 GB
BetterEmbeddingGemma 300MunstatedOpen+21%-90%$0.002Max input: 8K tokens → 2K tokens+1cOpenF2LLM v2 8Bunstated+40%——Memory (4-bit): 0.1 GB → 4.5 GBiCheaperMultilingual E5 Large InstructunstatedOpen+25%-50%$0.01Max input: 8K tokens → 1K tokens+1
Llama Embed Nemotron 8BOpen+34%——Memory (4-bit): 0.1 GB → 4.5 GB