Jina AI embedding model

jina-embeddings-v5-omni-nano

Jina v5 Omni Nano

Jina v5 Omni Nano is the compact model of Jina AI's v5-omni family, embedding text, images, video and audio into one vector space. its text output is bit-identical to jina-embeddings-v5-text-nano, at the same price.

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, images, video, audio, pdf
multilingual
yes
weights
open — CC BY-NC 4.0
released
May 7, 2026
model id
jina-embeddings-v5-omni-nano

integration notes

  • text input is capped at 8K tokens; images and audio go through their own encoders.
  • video is embedded as 32 uniformly sampled frames.

04

benchmarks

as published by the maker; not measured by octomind.

benchmarkscore
MMTEB (task-level average)source65.5
MTEB (English)source71.0
MIEB (Image)source47.87
MMEB-Video (Video)source29.73
MAEB (Audio)source49.69

05

when to pick it

pick it if

  • you want vectors in the same text space as v5-text-nano
  • you want the omni family at $0.02/M, below omni-small's $0.05/M
  • you want 768-dimension vectors truncatable down to 32

06

where it sits on price

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

07

use Jina v5 Omni 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-omni-nano"
text_model = "octohub:jina-embeddings-v5-omni-nano"

08

compare Jina v5 Omni Nano

all model comparisons →

09

similar embeddings

nearest embedding models by price.

view all models →

10

Jina v5 Omni Nano faq

how much does jina-embeddings-v5-omni-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-omni-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 Omni 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 Omni Nano with octocode?

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

use Jina v5 Omni Nano in octomind

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