Gemini Embedding model

A specialized engine for high-dimensional vector representation, providing efficient numerical mapping of text and images. The Gemini Embedding model is best for semantic search, document retrieval, and recommendation systems that require fast, scalable similarity calculations across large datasets.

Documentation

Visit the Embeddings page for full coverage of features and capabilities.

gemini-embedding-001

Property Description
Model code

Gemini API

gemini-embedding-001
Supported data types

Input

Text

Output

Text embeddings
Token limits[*]

Input token limit

2,048

Output dimension size

Flexible, supports: 128 - 3072, Recommended: 768, 1536, 3072
Versions
Read the model version patterns for more details.
  • Stable: gemini-embedding-001
Latest update June 2025