Jina AI embedding model

jina-embeddings-v5-text-nano

Jina v5 Text Nano

Jina v5 Text Nano is the smaller of Jina AI's two v5 text embedding models, a 239M-parameter multilingual model built on EuroBERT-210M. it costs less than jina-embeddings-v5-text-small and reads 8K tokens against Small's 32K.

01

price

$0.02/M

per 1M input tokens

embeddings bill input only — there are no output tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).

02

what real work costs

workloadcost
index 10,000 help articles ~800 tokens each, 8M tokens $0.16
index a 1M-line codebase ~10 tokens a line, 10M tokens $0.20
embed 1M search queries ~20 tokens each, 20M tokens $0.40

at the listed price. re-embedding after a model change costs the same again.

03

specs

provider
Jina AI
max input
about 8k tokens per text
dimensions
768 by default; also 32, 64, 128, 256 and 512
storage per 1M vectors
3.1 GB at 768 dims · 2 GB at 512 dims · 1 GB at 256 dims (float32)
accepts
text
multilingual
yes
weights
open — CC BY-NC 4.0
released
February 18, 2026
model id
jina-embeddings-v5-text-nano

integration notes

  • input over the 8K-token limit returns an error unless truncate is true; truncate defaults to false.
  • task defaults to text-matching; send retrieval.query for queries and retrieval.passage for documents.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
English MTEBsource71.0
MMTEB (multilingual)source65.5
RTEBsource64.08
BEIRsource56.06
LongEmbedsource63.65

05

when to pick it

pick it if

  • you want the cheapest Jina v5 text embeddings for multilingual search
  • Jina's reported English MTEB 71.0, near v5-text-small's 71.7, is enough
  • you want 768-dimension vectors that truncate down to 32 dimensions

06

where it sits on price

tied for the lowest price among the 10 embedding models in the catalog.

07

use Jina v5 Text Nano in octomind

octocode, octomind's semantic code search, takes any octohub embedding model by id. one octohub key covers it.

octocode config.toml
[embedding]
code_model = "octohub:jina-embeddings-v5-text-nano"
text_model = "octohub:jina-embeddings-v5-text-nano"

08

compare Jina v5 Text Nano

all model comparisons →

09

similar embeddings

nearest embedding models by price.

view all models →

10

Jina v5 Text Nano faq

how much does jina-embeddings-v5-text-nano cost?

$0.02/M input tokens; embeddings have no output charge. index a 1M-line codebase (~10 tokens a line, 10M tokens) costs about $0.20.

how many dimensions does jina-embeddings-v5-text-nano have?

768 by default; also 32, 64, 128, 256 and 512. at the default size, one million float32 vectors take 3.1 GB.

what is the maximum input length of Jina v5 Text Nano?

about 8k tokens per text (≈ 10 pages of prose or 1,000 lines of code). longer documents need chunking before embedding.

how do i use Jina v5 Text Nano with octocode?

set code_model and text_model to "octohub:jina-embeddings-v5-text-nano" in the [embedding] section of octocode's config.toml, then re-index.

use Jina v5 Text Nano in octomind

use it for semantic code search with octocode, or call it through octohub.