model comparison

vs

jina-embeddings-v5-omni-nano vs jina-embeddings-v5-omni-small

compared on price, indexing cost, vector size and input limits.

the short answer

  • on MMTEB (task-level average), as each maker reports it, jina-embeddings-v5-omni-nano scores 65.5 and jina-embeddings-v5-omni-small 67.0.
  • Jina v5 Omni Nano is cheaper: $0.02/M against $0.05/M.
  • Jina v5 Omni Small takes longer inputs (32k tokens against 8k tokens), so it needs less chunking.
  • Jina v5 Omni Nano returns smaller vectors (768 against 1024 dimensions), which cuts index storage by 25%.

side-by-side specs

specjina-embeddings-v5-omni-nanojina-embeddings-v5-omni-small
providerJina AIJina AI
price$0.02/M$0.05/M
max input8k tokens32k tokens
default dimensions7681,024
storage per 1M vectors3.1 GB4.1 GB
acceptstext, images, video, audio, pdftext, images, video, audio, pdf
multilingualyesyes
weightsopen (CC BY-NC 4.0)open (CC BY-NC 4.0)
MMTEB (task-level average) (maker-reported)65.567.0
MTEB (English) (maker-reported)71.071.7
MAEB (Audio) (maker-reported)49.6949.96

same work, both models

workloadjina-embeddings-v5-omni-nanojina-embeddings-v5-omni-small
index 10,000 help articles~800 tokens each, 8M tokensJina v5 Omni Small costs 2.5× as much$0.16$0.40
index a 1M-line codebase~10 tokens a line, 10M tokens$0.20$0.50
embed 1M search queries~20 tokens each, 20M tokens$0.40$1.00

at listed rates. re-embedding an index costs the same again.

when to pick which

jina-embeddings-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.

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

skip it if

  • you need more than 8K text tokens per input; omni-small takes 32K
  • you run commercially on self-hosted weights; the licence is non-commercial

jina-embeddings-v5-omni-small

Jina v5 Omni Small is Jina AI's multimodal embedding model for text, images, video, audio and PDF in one vector space. it extends jina-embeddings-v5-text-small, returns matching text vectors at the same price, and has a cheaper sibling, omni-nano.

pick it if

  • you search images, video, audio or PDFs alongside text in one index
  • you already index with v5-text-small; its text vectors match
  • you want 1024-dimension vectors that truncate down to 32

skip it if

  • you embed only text; v5-text-small gives matching vectors
  • short inputs fit omni-nano, which costs less per token

faq

which is cheaper, Jina v5 Omni Nano or Jina v5 Omni Small?

Jina v5 Omni Nano is cheaper: $0.02/M against $0.05/M.

which handles longer documents?

Jina v5 Omni Small takes longer inputs (32k tokens against 8k tokens), so it needs less chunking.

can i switch from Jina v5 Omni Nano to Jina v5 Omni Small without re-indexing?

no. vectors from different embedding models are not comparable, so a switch means re-embedding the whole corpus.

try either model

switch between models inside the same octomind session.

prices from the catalog of 2026-11-18