Repository Public
1# Gemini Embedding model23<br />45A specialized engine for high-dimensional vector representation, providing6efficient numerical mapping of text and images. The Gemini Embedding model is7best for semantic search, document retrieval, and recommendation systems that8require fast, scalable similarity calculations across large datasets.910## Documentation1112Visit the [Embeddings](https://ai.google.dev/gemini-api/docs/embeddings) page for full coverage13of features and capabilities.1415## gemini-embedding-0011617| Property | Description |18|---|---|19| Model code | **Gemini API** `gemini-embedding-001` |20| Supported data types | **Input** Text **Output** Text embeddings |21| Token limits^[\[\*\]](https://ai.google.dev/gemini-api/docs/tokens)^ | **Input token limit** 2,048 **Output dimension size** Flexible, supports: 128 - 3072, Recommended: 768, 1536, 3072 |22| Versions | Read the [model version patterns](https://ai.google.dev/gemini-api/docs/models/gemini#model-versions) for more details. - Stable: `gemini-embedding-001` |23| Latest update | June 2025 |