Gemini Embedding

Closed weights Google DeepMind July 2025

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
Google DeepMind
Organisation type
Industry
Country
United States of America
Published
14 July 2025
Authors
Jinhyuk Lee, Feiyang Chen, Sahil Dua, Daniel Cer, Madhuri Shanbhogue, Iftekhar Naim, Gustavo Hernández Ábrego, Zhe Li, Kaifeng Chen, Henrique Schechter Vera, Xiaoqi Ren, Shanfeng Zhang, Daniel Salz, Michael Boratko, Jay Han, Blair Chen, Shuo Huang, Vikram Rao, Paul Suganthan, Feng Han, Andreas Doumanoglou, Nithi Gupta, Fedor Moiseev, Cathy Yip, Aashi Jain, Simon Baumgartner, Shahrokh Shahi, Frank …

What it does

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

Domain
Language
Task
Semantic embedding

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

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

https://developers.googleblog.com/en/gemini-embedding-available-gemini-api/

How it is classified

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

Why it is tracked
SOTA improvement

Table 1 "This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March."

Record confidence
Unknown

Sources

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

Reference
Gemini Embedding: Generalizable Embeddings from Gemini
Last updated
28 November 2025

What the numbers mean

About this model

Gemini Embedding was published by Google DeepMind, in United States of America, in July 2025. industry is the category the publisher falls under.

It works in Language, and is recorded as doing semantic embedding.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

The reason it appears in this catalogue at all is sOTA improvement.

Answers

Gemini Embedding — common questions

01

Who created Gemini Embedding?

Gemini Embedding was published by Google DeepMind, based in United States of America, categorised as industry.

02

When was Gemini Embedding released?

Gemini Embedding was published in July 2025.

03

What is Gemini Embedding used for?

Gemini Embedding works in Language, and is recorded as handling semantic embedding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

What GPU do I need to run Gemini Embedding?

None. Gemini Embedding 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.

05

Is Gemini Embedding open source?

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

06

How many parameters does Gemini Embedding have?

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

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.