Gemini Embedding 2
Gemini Embedding 2 is a text embedding model from Google designed to convert text into dense vector representations.
GoogleText embeddings with 8K token context
Gemini Embedding 2 is a text embedding model developed by Google, available through Vertex AI. It accepts text input and produces dense vector representations that capture semantic meaning, enabling downstream tasks such as semantic search, document retrieval, clustering, and classification. The model supports a context window of 8,192 tokens, allowing it to process longer passages of text in a single embedding call.
This model is suited for developers and organizations building retrieval-augmented generation (RAG) pipelines, recommendation systems, or any application that requires measuring semantic similarity between pieces of text. Because it is a first-party Google model served through Vertex AI, it integrates directly with Google Cloud infrastructure. Pricing details were not publicly listed at the time of this writing, so developers should consult the Vertex AI pricing page for current rates.
What Gemini Embedding 2 supports
Text Embedding
Converts input text into dense vector representations that encode semantic meaning. Supports inputs up to 8,192 tokens in a single call.
Semantic Search
Enables similarity-based retrieval by comparing embedding vectors across a corpus of documents. Commonly used in RAG pipelines and search applications.
Document Clustering
Groups semantically related documents by comparing their vector representations in embedding space. Useful for topic modeling and content organization.
Long Context Input
Processes text passages up to 8,192 tokens in a single embedding request, accommodating longer documents without chunking.
Vertex AI Integration
Served as a first-party model on Google Cloud's Vertex AI platform, enabling direct integration with Google Cloud services and IAM-based access control.
Ready to build with Gemini Embedding 2?
Get Started FreeCommon questions about Gemini Embedding 2
What is the context window for Gemini Embedding 2?
Gemini Embedding 2 supports a context window of 8,192 tokens, meaning it can process up to 8,192 tokens of text in a single embedding request.
What type of model is Gemini Embedding 2?
It is a text embedding model, meaning it takes text as input and outputs dense numerical vectors that represent the semantic content of that text. It does not generate text responses.
How is Gemini Embedding 2 accessed?
The model is available through Google Cloud's Vertex AI platform as a first-party Google model. Access is managed through Google Cloud credentials and IAM permissions.
What is the pricing for Gemini Embedding 2?
Pricing was not publicly listed in the available metadata. Developers should refer to the Vertex AI pricing page on Google Cloud for current rates.
What are common use cases for Gemini Embedding 2?
Common use cases include semantic search, retrieval-augmented generation (RAG), document clustering, text classification, and recommendation systems — any task that benefits from comparing semantic similarity between text inputs.
Explore similar models
GoogleEmbeddingGemma 300M
EmbeddingGemma 300M is a 300-million-parameter text embedding model from Google with a 2048-token context window.
GoogleGemini Embedding
Gemini Embedding is a text embedding model from Google that converts text into vector representations with a 2048-token context window.
GoogleGemini 3.7 Flash
Gemini 3.7 Flash is a text generation model from Google with a 1,048,576-token context window and configurable thinking levels.
PerplexityPerplexity Embed v1 0.6B
Perplexity Embed v1 0.6B is a quantized embedding model from Perplexity with a 32,000-token context window.
Voyage AIVoyage 4
Voyage 4 is an embedding model from Voyage AI designed for semantic search and retrieval with a 32,000-token context window.
QwenQwen3 Embedding 0.6B
Qwen3 Embedding 0.6B is a compact embedding model from Qwen with a 32,768-token context window, served via DeepInfra.
Start building with Gemini Embedding 2
No API keys required. Create AI-powered workflows with Gemini Embedding 2 in minutes — free.