Google DeepMind
Google DeepMind
Embedding model · United States ·Mar 2026

Gemini Embedding 2

Embedding Proprietary
8.2K
Context

About Gemini Embedding 2

Gemini Embedding 2 is an AI model developed by Google DeepMind, in the embedding category, released in 2026, made available as a proprietary (API-only) model. Google's first natively multimodal embedding model, mapping text, images, video, audio and PDF documents into a single s.

On this page you'll find Gemini Embedding 2's full specifications, including a context window of 8.2K tokens. Review provider pricing and benchmark scores below, or compare Gemini Embedding 2 head-to-head with other embedding models.

Community

Would you run Gemini Embedding 2 again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Gemini Embedding 2

Frequently asked questions

What is Gemini Embedding 2?

Google's first natively multimodal embedding model, mapping text, images, video, audio and PDF documents into a single s It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Gemini Embedding 2?

Gemini Embedding 2 was developed by Google DeepMind and released in 2026.

Is Gemini Embedding 2 open source or proprietary?

Gemini Embedding 2 is a proprietary model. It is accessed through an API rather than by downloading the weights.

What is Gemini Embedding 2's context window?

Gemini Embedding 2 supports a context window of 8.2K tokens.

How much does Gemini Embedding 2 cost?

Pricing for Gemini Embedding 2 depends on the provider. See the providers table on this page for the latest API rates.

How does Gemini Embedding 2 perform on benchmarks?

Benchmark scores for Gemini Embedding 2 are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about Gemini Embedding 2?