Skip to content

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

Reasoning Very low
Coding Very low
Vision Very low
Speed High
Price level Low
Context size Medium
Tool calling Very low
Structured output Very low

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

Knowledge search

Search across manuals, policies and tickets. See knowledge base search.

MongoDB projects

Embeddings for teams already using MongoDB Atlas.

Code search

Searching code with the dedicated code model.

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

FAQ

Questions people ask us

Have a question that is not here? Ask us directly.

Start a project

Not sure which model fits? Ask us to evaluate your use case.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.