Cohere Embed

Closed weights Cohere November 2023

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Cohere
Organisation type
Industry
Country
Canada
Published
2 November 2023
Authors
Nils Reimers, Elliott Choi, Amr Kayid, Alekhya Nandula, Manoj Govindassamy, Abdullah Elkady

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Semantic embedding, Retrieval-augmented generation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

"First, they have been trained on questions and answers from a large web crawl. When we presented our multilingual-v2.0 model last year, we had a collection of over 1.4 billion question-and-answer pairs from 100+ languages on basically every topic on the internet." "Hence, the second stage involved measuring content quality. We used over 3 million search queries from search engines and retrieved the top-10 most similar documents for each query."

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
API access
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Why it is tracked
SOTA improvement

"We are releasing new English and multilingual Embed versions with either 1024 or 384 dimensions. All models can be accessed via our APIs. As of October 2023, these models achieve state-of-the-art performance among 90+ models on the Massive Text Embedding Benchmark (MTEB) and state-of-the-art performance for zero-shot dense retrieval on BEIR."

Record confidence
Unknown

Sources

Where this record came from and when it was last checked.

Reference
Cohere Command & Embed on Amazon Bedrock
Last updated
28 November 2025

What the numbers mean

Where it came from

Cohere Embed was published by Cohere, in Canada, in November 2023. industry is the category the publisher falls under.

It works in Language, and is recorded as doing semantic embedding, Retrieval-augmented generation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

Cohere Embed — common questions

01

What is Cohere Embed used for?

Cohere Embed works in Language, and is recorded as handling semantic embedding, Retrieval-augmented generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

02

What GPU do I need to run Cohere Embed?

None. Cohere Embed is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

03

Is Cohere Embed open source?

No. Cohere Embed has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does Cohere Embed have?

No parameter count has been published for Cohere Embed, which is why no memory or speed figure appears on this page.

05

Who created Cohere Embed?

Cohere Embed was published by Cohere, based in Canada, categorised as industry.

06

When was Cohere Embed released?

Cohere Embed was published in November 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.