Post-Cutoff
Search For AI agents

Google DeepMindGemini Embedding familyCurrentEmbedding modelReleased 22 Apr 2026

Gemini Embedding 2

Embeddings for multimodal RAG, semantic search, clustering and classification.

Model idgemini-embedding-2

Price$0.20 in per 1M tokens

Checked29 September 2026

Where it stands

3newer embedding models since its release

All embedding models

After it from Google
EmbeddingGemma 26 Oct 2026
Weights
Closed weights; access is hosted only.

How to call it

2 ways to use Gemini Embedding 2, with the model id each provider expects.

Providers, model ids, endpoints and docs for Gemini Embedding 2
ProviderModel idEndpointDocs
Gemini API gemini-embedding-2 https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent ai.google.dev
Google Cloud Gemini Enterprise Agent Platform (Vertex AI) docs.cloud.google.com

Pricing

Prices for Gemini Embedding 2
Input$0.20 per 1M tokens

As published: “per 1M text input tokens; image $0.45/1M (~$0.00012 per image), audio $6.50/1M (~$0.00016/s), video $12.00/1M (~$0.00079 per frame)”.

Source: ai.google.dev, checked 29 September 2026.

Specs

Input
Text, images, audio, video and PDF
Output
Text
Context window
8,192 tokens
Max output
Not published
Open weights
No
Licence
Proprietary
Released
22 April 2026
Status
Current
Type
Embedding model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Natively multimodal embeddings

    Text, images, video, audio and PDFs mapped into one embedding space; Google’s first natively multimodal embedding model and first in the Gemini API.

    Source: ai.google.dev

  • Matryoshka dimensions

    Flexible 128-3072 output dimensions (recommended 768/1536/3072); 100+ languages.

    Source: ai.google.dev

Notes

Public preview March 2026 (id gemini-embedding-2-preview, still listed), GA 2026-04-22. modality_out ‘text’ is a placeholder: output is a vector. Predecessor gemini-embedding-001 (text-only) shuts down 2028-05-14.

from google import genai
client = genai.Client()
r = client.models.embed_content(model="gemini-embedding-2", contents="What is the meaning of life?")

Sources: embeddings guide, pricing, deprecations, launch blog.