Voyage 4 Lite
Voyage 4 Lite is a text embedding model from Voyage AI supporting a 32,000-token context window for semantic search and retrieval tasks.
Voyage AILightweight text embeddings with large context
Voyage 4 Lite is a text embedding model developed by Voyage AI, designed to convert text into dense vector representations for use in semantic search, retrieval-augmented generation (RAG), and similarity tasks. It supports a context window of 32,000 tokens, allowing it to process longer documents in a single pass without chunking. Released in 2026, it is offered as a first-party model through Voyage AI's embedding API.
The "Lite" designation indicates this model is positioned as a lighter-weight option within the Voyage 4 embedding family, making it suitable for applications where efficiency and lower computational cost are priorities alongside reasonable embedding quality. It is best suited for developers building search pipelines, recommendation systems, or document retrieval workflows that require embedding large volumes of text. Because it is an embedding model, it produces vector outputs rather than generated text and does not support conversational or generative tasks.
What Voyage 4 Lite supports
Text Embeddings
Converts input text into dense vector representations for downstream tasks like semantic search and clustering. Outputs fixed-dimensional vectors suitable for similarity comparison.
Long Context Support
Processes documents up to 32,000 tokens in a single embedding pass, reducing the need to split long documents into smaller chunks.
Retrieval-Augmented Generation
Produces embeddings optimized for RAG pipelines, enabling efficient retrieval of relevant document passages to ground language model responses.
Semantic Similarity
Encodes text such that semantically related passages produce vectors with high cosine similarity, supporting tasks like duplicate detection and recommendation.
API Integration
Accessible via Voyage AI's REST API, allowing embedding requests to be integrated into existing applications without managing model infrastructure.
Ready to build with Voyage 4 Lite?
Get Started FreeCommon questions about Voyage 4 Lite
What is the context window for Voyage 4 Lite?
Voyage 4 Lite supports a context window of 32,000 tokens, meaning it can embed documents of up to that length in a single request.
What type of model is Voyage 4 Lite?
Voyage 4 Lite is a text embedding model. It generates vector representations of text and does not produce generated or conversational text output.
What is Voyage 4 Lite best used for?
It is best suited for semantic search, retrieval-augmented generation (RAG), document similarity, and clustering tasks that require embedding large volumes of text efficiently.
How is Voyage 4 Lite different from other Voyage 4 models?
The "Lite" designation indicates it is a lighter-weight variant within the Voyage 4 embedding family, intended for use cases where efficiency and lower resource usage are priorities.
What is the pricing for Voyage 4 Lite?
Pricing information for Voyage 4 Lite is not published in the available metadata. Check the Voyage AI website or documentation for current pricing details.
Does Voyage 4 Lite support image or multimodal inputs?
Based on available metadata, Voyage 4 Lite is a text embedding model and does not indicate support for image or video inputs.
Explore similar models
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.
Voyage AIVoyage 4 Large
Voyage 4 Large is an embedding model from Voyage AI with a 32,000 token context window for semantic search and retrieval.
Voyage AIVoyage Code 4
Voyage Code 4 is a code-specialized embedding model from Voyage AI with a 32,000 token context window.
PerplexityPerplexity Embed v1 0.6B
Perplexity Embed v1 0.6B is a quantized embedding model from Perplexity with a 32,000-token context window.
GoogleGemini Embedding 2
Gemini Embedding 2 is a text embedding model from Google designed to convert text into dense vector representations.
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 Voyage 4 Lite
No API keys required. Create AI-powered workflows with Voyage 4 Lite in minutes — free.