Supercharging
Search and Retrieval
for Unstructured Data

Union

Best-in-class embedding models and rerankers

Try it now

Embeddings and Rerankers Drive RAG Retrieval and Response Quality

  • Unstructured data iconUnstructured data
  • connector
  • Embedding model iconEmbedding model
  • connector
  • Vector DB iconVector DB
  • connector
  • Reranker iconReranker
  • connector
  • Relevant files iconRelevant files
  • connector
  • LLM iconLLM
  • connector
  • Factual responses iconFactual responses with lower costs

A Spectrum of Models for Your Target Use Cases

General-purpose models icon

General-purpose models

Ready for any purpose and language out-of-the-box.

Get started
Domain-specific models icon

Domain-specific models

Highly optimized for industry-specific data, like finance, legal, and code.

Get started
Company-specific models icon

Company-specific models

Fine-tuned librarians for your company's unique data and lingo.

Contact Sales

Powered by Cutting-Edge AI Research and Engineering

High accuracy icon

High accuracy

Retrieving the most relevant contextual information

Low dimensionality icon

Low dimensionality

3x-8x shorter vectors => cheaper vector search and storage

Low latency icon

Low latency

4x smaller model and faster inference with superior accuracy

Cost efficient icon

Cost efficient

2x cheaper inference with superior accuracy

Long-context icon

Long-context

Longest commercial context length available (32K tokens)

Modularity icon

Modularity

Plug-and-play with any vectorDB and LLM

Trusted by Industry Leaders

Continue
"Continue allows engineers to converse with entire codebases and beyond, making Voyage AI's code embedding model a natural choice for our use case. The combined performance of voyage-code-2 plus rerank-lite-1 in our benchmarks made working with Voyage AI a no-brainer, and they have proven to offer unmatched accuracy and stability."
Nate Sesti

Nate Sesti

Co-Founder

Harvey
"Harvey has partnered with Voyage AI to create custom legal embeddings tailored to Harvey's use cases. We chose Voyage because their voyage-law-2 legal embedding model has already demonstrated best-in-class performance on public legal retrieval benchmarks. Fine-tuning the model with Harvey's specific datasets reduces the irrelevant document rate by 25% and decreases the dimensionality of the embeddings and the vectorDB costs by threefold."
Gabe Pereyra

Gabe Pereyra

President & Co-Founder

Replit
"Excellent code retrieval accuracy is crucial for Replit Agent, as it allows us to always put in context the most relevant files depending on the action type. The Voyage AI team has deep expertise developing embedding models for domain-specific retrieval, and the state-of-the-art performance attained by voyage-3 will give us the best overall performance for our code retrieval tasks."
Michele Catasta

Michele Catasta

President of Replit

Snowflake
"At Snowflake, we're dedicated to delivering exceptional customer experiences. That's why we've partnered with Voyage AI, whose embedding models have consistently demonstrated unmatched quality in real-world applications. By integrating Voyage AI's superior technology with the security, efficiency, and governance of Snowflake's Data Cloud, we're unlocking unparalleled Retrieval-Augmented Generation (RAG) experiences for our customers. With Voyage AI's best-in-class models now available as native features within our platform, we're setting a new standard for AI-driven innovation and customer satisfaction."
Vivek Raghunathan

Vivek Raghunathan

SVP of Engineering

Kapa.ai
"End user experience is extremely important to us at Kapa.ai, and a big part of that is making sure our AI assistants are grounded with reliable sources of knowledge. Voyage AI's powerful reranker made a big difference for us - not only did it perform the best, but it was also easy to integrate into our existing stack, unlocking significant performance gains and enabling highly accurate retrieval-augmented generation at a low cost."
Finn Bauer

Finn Bauer

Co-Founder

Xayn/Noxtua
"Our collaboration with Voyage AI to launch Noxtua Voyage Embed marks a significant step in advancing specialized, high-quality legal AI solutions, demonstrating a 1.7x better retrieval accuracy than OpenAI's latest text-embedding-3-large embedding model on legal benchmarks. This cross-border collaboration has allowed us to further develop Noxtua, Europe's first independent legal AI, to better assist lawyers in their everyday tasks."
Leif-Nissen Lundbæk PhD

Leif-Nissen Lundbæk, PhD

CEO & Co-Founder

DatabricksAnthropicReplitKapaXaynContinueZillizWeaviateLangChainHarveySnowflakeDataStaxAWSLlamaIndexQdrantChromaRedisUnstructuredDatabricksAnthropicReplitKapaXaynContinueZillizWeaviateLangChainHarveySnowflakeDataStaxAWSLlamaIndexQdrantChromaRedisUnstructured

© 2026 MongoDB, Inc. All rights reserved.