Cohere Embed 5 Pro
Cohere's new search embedding model for text, images and PDFs. No independent scores yet; wait for MTEB results.
Should you use it?
Pick it if
Teams building search or retrieval over documents with images, who can wait for outside benchmarks.
Skip it if
You need a choice backed by independent results today.
The short version
- What this is
- An embedding model: it turns text, images and PDF pages into vectors so search and AI assistants can find the right documents. Available on Cohere's API, Microsoft Foundry and Amazon SageMaker.
- Why it matters
- Embeddings decide what an AI search finds; this one handles images and PDFs, but its quality is not yet checked by anyone outside Cohere.
- Launched 30 Sep 2026 with a faster sibling, Embed 5 Fast s4.
- Text, images and PDFs, 128k context s1.
- No independent benchmark yet, so no score yet.
Good at
Our take
Cohere released Embed 5 on 30 Sep 2026 in two sizes, covered by The New Stack and AI Magazine s4 s5. Pro is the higher quality one, for text, images and mixed pages s1. A useful detail is that you can index documents with Pro and search them with the cheaper, faster Fast model s4.
We could not find it on MTEB or any other independent embedding benchmark, and the comparisons with Voyage and Gemini come from Cohere's own runs s4. Until outside results exist, test it on your own documents before switching.
Not scored yet
This is a First look: the call above comes from the maker's own pages, so there is no score yet. Once MTEB or another independent embedding benchmark lists it.
Research
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Alternatives
Better or cheaper for research, from our scores, then the ones we'd also look at. The same kind of product comes first.
- Gemini 4 ArgonTop scoredText model95$4.99 a monthScores 95 in research, first in our ranking; $4.99 a month. Side by side
- EmbeddingGemma 2Embedding modelFirst look: WaitFreeFree open-weights embedding model for text, images, audio and video; also waiting on independent scores. Side by side
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 5
- s1Cohere docs: models overview
- s2Cohere pricing
- s3Cohere data usage policy
- s4The New Stack: Cohere Embed 5 Pro and Fast
- s5AI Magazine: Cohere Embed 5
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- First look: no independent benchmark yet.
- Audit: swapped in EmbeddingGemma 2, a free alternative with its own page.
Use it well 3 guides on this site
Pages on this site that help with the jobs above.