Back to gemini
Google DeepMind /

Gemini Embedding 2
Gemini Embedding 2

API OnlyMultimodaltextimageaudiovideopdfUpdated April 22, 2026
Some details or benchmark scores on this page are self-reported by developers and unconfirmed.

Gemini Embedding 2

📌 Model Overview

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space

Gemini Embedding 2 is a Api Only model developed by Google DeepMind, released on 2026-04-22. It is designed primarily for Multimodal General workloads. Featuring a 8K tokens context window and Undisclosed parameter count, it offers robust performance for enterprise integration, developers, and researchers.


✨ Key Features & Capabilities

Specification Table
FeatureDescription
Context Window8K tokens capacity for extended prompts and multi-turn workflows
Primary TaskOptimized for Multimodal General
Deploymentapi-only
Modalitytext, image, audio, video, pdf
Max OutputMax Output: 3K tokens

⚙️ Technical Specifications

Specification Table
SpecificationDetails
Developer / LabGoogle DeepMind
Release Date2026-04-22
Model TypeApi Only
ParametersUndisclosed
Context Window8K tokens
LicenseProprietary
Model Familygemini

💰 Pricing

Specification Table
Tier / UnitRate (USD)
1M input tokens$0.2
1M output tokens$0

📜 License & Usage

This model is governed by the Proprietary license. Please check official developer guidelines before commercial deployment.

Key Features

Max Output: 3K tokens

Feature 01

You might also want to compare

Verified Sources

Model Specs

api-only

Parameters

Undisclosed

Context Window

8K tokens

License

Proprietary

Deployment

api-only

Pricing

  • 1M input tokens$0.2
  • 1M output tokens$0

as of 2026-07-26

Lineage

Curator Notes

Skeleton entry imported from models.dev backfill (2026-07-26). Needs manual enrichment and primary-source verification.

Compare Specs

Compare parameters, context windows, modalities, and benchmark scores of this model side-by-side with others.

Compare Model