Google DeepMind

Gemini Embedding 2

Generally availableProprietary8K context

Summary

Gemini Embedding 2 is a proprietary language model from Google DeepMind, released on 22 Apr 2026. It accepts text, images, audio, video and PDFs and generates text, with a 8K-token context window and up to 1 output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.20 per million input tokens and Free per million output tokens (Gemini API), across 2 providers we track.

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

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date22 Apr 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window8K (8,192 tokens) [models.dev]
Max output1 tokens [models.dev]
Knowledge cutoffNov 2025 [models.dev]
InputText, images, audio, video and PDFs [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

Gemini Embedding 2 API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Gemini API
gemini-embedding-2
$0.20Free–8Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
google/gemini-embedding-2
–––8Kmodels.dev, 18 Nov 2026

Frequently asked questions

What is the context window of Gemini Embedding 2?

Gemini Embedding 2 has a context window of 8,192 tokens (8K) and can generate up to 1 tokens in a single response, according to models.dev.

How much does the Gemini Embedding 2 API cost?

Through Gemini API, Gemini Embedding 2 costs $0.20 per million input tokens and Free per million output tokens. Prices last verified 18 Nov 2026.

Is Gemini Embedding 2 open source?

No. Gemini Embedding 2 is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API, Vercel AI Gateway.

When was Gemini Embedding 2 released?

Google DeepMind released Gemini Embedding 2 on 22 Apr 2026, according to models.dev.

Which providers offer Gemini Embedding 2?

We track Gemini Embedding 2 on 2 providers: Gemini API, Vercel AI Gateway.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
gpt-realtime-whisperOpenAI7 May 202616K––Closed
Schematron V2 TurboInference NET16 Apr 2026128K$0.03$0.15Closed
Mercury Edit 2Inception Labs30 Mar 202632K$0.25$0.75Closed
Schematron V2 SmallInference NET16 Apr 2026128K$0.05$0.23Closed
Grok Voice STT 1.0xAI4 Aug 202615K––Closed
Perceptron Mk1Perceptron12 May 202633K$0.15$1.50Closed

Change history

No changes detected since we started tracking this model. We re-check every source daily.

Sources