AI model by Voyage AI by MongoDB
Voyage 4 for business
Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
- Reviewed on September 24, 2026
- Voyage AI by MongoDB
Capability tiersRelative, not benchmarks
Key facts about Voyage 4
- Model ID at review
- voyage-4, voyage-4-large, voyage-4-lite
- Provider
- Voyage AI by MongoDB
- Main category
- Embeddings
- Open weights
- No, available as a hosted service
- Last reviewed
- September 24, 2026
Fit
Where it fits and where it does not
Good at
-
Search and retrieval for knowledge assistants.
-
A shared embedding space across sizes.
-
Indexing with a large model and querying with a lite one.
-
Flexible vector sizes from 256 to 2,048.
-
Specialized models for code and long context.
Not the right choice for
-
Images in the standard models, which are text only.
-
Generating answers.
-
Chunks longer than 32K tokens in the general models.
-
Projects that cannot re-embed later.
Use cases
Business use cases we would use it for
MongoDB projects
Code search
Our notes
When we would choose it
Voyage 4 was released in January 2026 and replaces the voyage-3 and voyage-3.5 models, which still work but are marked as previous generation. The series includes voyage-4-large for the best quality, voyage-4 as the general model and voyage-4-lite for the lowest cost. The general models are text only, with a 32K token context and vector sizes of 256, 512, 1,024 or 2,048.
The standout feature is that all Voyage 4 models share one embedding space. You can index documents once with the large model and search them with the lite model, which lowers the cost of every query without re-embedding the collection.
Voyage AI was acquired by MongoDB in 2025, and the product is now Voyage AI by MongoDB, billed through Atlas. For teams already on MongoDB, that makes it a natural choice. The series also includes models for code, long documents and multimodal content, and a small open-weight model, voyage-4-nano, whose license we did not verify.
We would compare Voyage 4 with OpenAI embeddings, Cohere Embed and Gemini Embedding on the same questions, then add reranking. See RAG knowledge assistants.
If you already embed with voyage-3, there is no urgent need to move, but new collections are a good time to start on Voyage 4. See embedding models.
Before you commit
Things to check before you commit
-
Retrieval test
Test on your own questions and compare with your current model.
-
Previous generation
voyage-3.5 and voyage-3-large still work but are marked previous generation.
-
Billing
Billing now runs through MongoDB Atlas.
-
Vector size
Choose a dimension that balances quality and storage.
Alternatives
Models to compare it with
text-embedding-3-large
OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
Cohere Embed v4
Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
Gemini Embedding 2
Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
Keep exploring
Solutions, services and guides
Related services
View all related services- RAG knowledge assistants Assistants that answer questions from your own documents and show where each answer came from.
- Database design Data models that stay fast and correct as your business grows, with backups and access rules in place.
- AI Product Development AI agents, knowledge assistants, copilots and document automation built into the way your team already works.
- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
Solutions
View all solutions- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- Forecasting dashboards Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
- AI support agent An assistant that answers routine questions from your own content, checks orders and hands anything else to a person.
- Payroll automation Turn pay rules, attendance and leave into tested software so the monthly run becomes a review and payslips go out in one batch.
Industries
View all industries- Healthcare Patient booking, intake forms, internal knowledge assistants and admin automation for clinics and care providers.
- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
Case studies
View all case studiesGuides and articles
View all guides and articles- What is RAG and when do you need it? How retrieval-augmented generation lets AI answer from your documents, when it fits and how to build it well.
- RAG vs fine-tuning Two ways to make AI work with your knowledge, compared by cost, accuracy and upkeep.
- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- PostgreSQL vs MySQL The two most popular open-source databases compared for business applications.
MCP servers
View all mcp servers- Chroma Chroma's official MCP server lets AI create collections, add, query, update and delete documents in a Chroma vector database, local or cloud.
- Confluence Atlassian's official Rovo MCP server lets AI search and read Confluence spaces and pages, create and edit content and add comments and labels.
- Memory The MCP project's Memory reference server gives AI a local knowledge graph to store people, things and facts and recall them later.
- Obsidian A community MCP server that lets AI list, read, search, edit, append to and delete notes in an Obsidian vault through the Local REST API plugin.
- Pinecone Pinecone's official developer MCP server lets AI search Pinecone docs, manage indexes, upsert records, search and rerank.
- Qdrant Qdrant's official MCP server gives AI a semantic memory: store information in a Qdrant collection and find it again by meaning.
Glossary terms
View all glossary terms- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
MongoDB acquired Voyage AI in 2025. The product is now Voyage AI by MongoDB.
Vectors from different Voyage 4 sizes can be compared, so you can index with one size and query with another.
They still work but are marked previous generation and not recommended for new work.