Voyage Law 2
Voyage Law 2 is an embedding model from Voyage AI optimized for legal text retrieval with a 32,000-token context window.
Voyage AILegal text embeddings with 32K context
Voyage Law 2 is a text embedding model developed by Voyage AI, designed specifically for legal applications such as case law retrieval, contract analysis, and legal document search. It accepts up to 32,000 tokens of input per request, making it capable of processing lengthy legal documents like briefs, contracts, and statutes in a single pass. The model is a first-party offering from Voyage AI and is available through their API.
The model is purpose-built for the legal domain, meaning its embeddings are trained to capture the semantic nuances of legal language, including jurisdiction-specific terminology, statutory references, and case citations. This domain specialization makes it well-suited for building retrieval-augmented generation (RAG) pipelines, legal research tools, and document similarity systems where general-purpose embeddings may underperform on legal text. Developers working on legal tech applications can use it as a drop-in embedding layer for vector search workflows.
What Voyage Law 2 supports
Legal Domain Embeddings
Generates vector embeddings tuned for legal language, capturing terminology found in case law, contracts, and statutes that general models may not handle well.
Long Document Context
Supports up to 32,000 tokens per input, allowing full legal documents such as briefs or contracts to be embedded without chunking.
Semantic Text Retrieval
Produces dense vector representations suitable for similarity search and retrieval-augmented generation (RAG) pipelines over legal corpora.
API Integration
Accessible via the Voyage AI REST API, allowing embedding requests to be integrated into existing vector database and search workflows.
Ready to build with Voyage Law 2?
Get Started FreeCommon questions about Voyage Law 2
What is the context window for Voyage Law 2?
Voyage Law 2 supports a context window of 32,000 tokens per input request, which is large enough to embed lengthy legal documents in a single call.
What type of model is Voyage Law 2?
Voyage Law 2 is an embedding model, meaning it converts text into dense numerical vectors rather than generating text. It is not a generative or chat model.
What is Voyage Law 2 best suited for?
It is optimized for legal domain tasks such as case law retrieval, contract similarity search, legal document classification, and building RAG pipelines over legal corpora.
Who publishes Voyage Law 2?
Voyage Law 2 is published and provided by Voyage AI as a first-party model available through their API.
Is pricing information available for Voyage Law 2?
Specific pricing was not included in the available metadata. You should consult the Voyage AI documentation or pricing page for current rates.
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 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.
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 Law 2
No API keys required. Create AI-powered workflows with Voyage Law 2 in minutes — free.