Using Gemini Embedding 2 on Google AI Studio

Quick Start

1. 1
   Create an account at Google AI Studio and generate an API key.
2. 2
   Use the Google AI Studio SDK or REST API to call gemini-embedding-2 — see the documentation for request format.
3. 3
   You'll be billed $0.20/1M input, Free/1M output tokens.

Code Examples

import os
from google import genai

client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
response = client.models.generate_content(
    model="gemini-embedding-2",
    contents="Hello"
)
print(response.text)

About Google AI Studio

Model prototyping and API access to Gemini models with inference playground

Pricing on Google AI Studio

Capabilities

About Gemini Embedding 2

General availability release of Google's multimodal embedding model, released April 22, 2026. Generates 3072-dimensional vectors from text, images, documents, audio, and video inputs, mapping all modalities into a unified semantic space. Supports custom task instructions to optimize embeddings for retrieval, classification, clustering, or other goals. Output dimensionality is configurable via the output_dimensionality parameter. Priced at $0.20/1M input tokens. Distinct from gemini-embedding-2-preview (the earlier preview version). API ID: gemini-embedding-2.