GE

Gemini Embedding 2

Embedding modelGemini EmbeddingGemini Embedding 2

Gemini Embedding 2

Release date: 2026-03-10319
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
8K
Chinese support
Not supported
Reasoning ability

Gemini Embedding 2 is an AI model published by Google Deep Mind, released on 2026-03-10, for Embedding model, and 8K context length, under the 不开源 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemini Embedding 2

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
8K tokens
Max output length
3K tokens
Model type
Embedding model
Modality (in / out)
Text, Image, Audio, Video, Embedding → Text, Embedding
Release date
2026-03-10
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Gemini Embedding 2

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
Gemini Embedding 2

Official resources

Gemini Embedding 2

API details

API speed
4/5
No public API pricing yet.
Gemini Embedding 2

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Gemini Embedding 2

Publisher

Google Deep Mind
View publisher details
Gemini Embedding 2

Model Overview

Gemini Embedding 2 is an AI model published by Google Deep Mind, released on 2026-03-10, for Embedding model, and 8K context length, under the 不开源 license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code