NEWLevel up your AI skills with 3 new free, focused MongoDB gen AI credentials Earn a skill badge > >>
GUIDEHow to build a movie recommendation engine with Voyage AI and Hugging Face Read the blog > >>

AI MODELS

Voyage AI by MongoDB

Build trustworthy, production-grade AI applications and agents with best-in-class embedding models—accessible via standalone API or natively in Atlas.

Try Free
Start building now

High-accuracy retrieval for production AI agents

Maximize your retrieval performance with state-of-the-art accuracy that reduces hallucinations across complex and multimodal data.

  • State-of-the-art retrieval accuracy
  • Database agnostic
  • High performance, low latency
Voyage AI data illustration

High accuracy embeddings and rerankers

Ground your AI applications and agents with high-accuracy retrieval, powered by state-of-the-art models and advanced capabilities like contextualized chunk embeddings and instruction following.

Precision reranking for optimized retrieval

Refine your results to maximize retrieval quality. Leverage the power of cross-encoders capable of instruction following.

Close the modality gap across all your data

Project text, screenshots, PDFs, and video into a single unified vector space. Designed for systems architects and engineering teams building workflows that must look beyond raw text to parse complex, multimodal documents natively without loss of semantic context.

Start flexible. Simplify with confidence.

Start with the flexibility of a database-agnostic API that fits your stack today. As your workflows mature and your needs grow, seamlessly adopt integrated capabilities that simplify operations and reduce coordination across services—secure and governed from day one.

Optimize price performance

Cutting-edge research delivers models at the price-performance frontier. Right-size inference and storage costs without compromising retrieval quality through flexible output dimensions, quantization, and a range of model sizes tailored to your requirements.

Deployment flexibility

Overcome infrastructure constraints with flexible deployment controls designed for multi-geo and privacy-first operations. Run workloads seamlessly on standard managed cloud APIs, private VPCs, or air-gapped on-premises infrastructure to meet strict compliance mandates.

Architectural flexibility. Operational simplicity.

Build your agent your way. Use a standalone, database-agnostic API or native Atlas integration for a unified stack and simpler operations. Minimize lock-in or move to a simpler, fully integrated operational experience without changing models.

Maintain absolute stack independence. Our database-agnostic API works seamlessly with any vector-capable database or AI framework across your chosen cloud architecture, ensuring your embeddings remain portable and entirely free from vendor lock-in.

Get started
Python

Innovators choose Voyage AI

View all customers
GEN AI
“We were looking for extremely accurate embedding models, and Voyage AI provided accuracy at scale. The Python APIs that Voyage comes out of the box with are also extremely lightweight and very fast. When it comes to document storage, when it comes to unstructured data, MongoDB is the place. It’s the bookend for value creation and value delivery.”
Sudheesh Nair
Cofounder and CEO, TinyFish
Read Story
GEN AI
“We were looking for extremely accurate embedding models, and Voyage AI provided accuracy at scale. The Python APIs that Voyage comes out of the box with are also extremely lightweight and very fast. When it comes to document storage, when it comes to unstructured data, MongoDB is the place. It’s the bookend for value creation and value delivery.”
Sudheesh Nair
Cofounder and CEO, TinyFish
Read Story
GEN AI
“We started working with Voyage before its acquisition by MongoDB and immediately saw that it outperformed other embedding models, so we made the switch. We were very excited because we were able to use the new model in a bunch of code‑retrieval benchmarks. Until that point, we’d not seen any other embedding model that even made a dent in retrieval performance. Voyage is now core to our entire platform.”
Eno Reyes
Co-founder and CTO, Factory
Read Story
96%time reduction in planning experiences
15 millioncustomers served
MODERNIZATION
“MongoDB Atlas is the silver bullet. It’s a solution for your database, your search, and now it’s providing AI tools. It’s taken us beyond operational transformation to a solution that we’re rolling out everywhere.”
Muhammad Ali Khan
Group Head of Technology, TUI Musement
Read Story
90%latency reduction
65%operational cost reduction
CONTENT MANAGEMENT
“We needed a solution that was going to scale much better. We already had storage on MongoDB, and it made sense to simply use MongoDB to process vectors instead of sending the data to an external pipeline.”
Chris Chen
Global VP of Architecture and Governance, Condé Nast
Read Story
40%accuracy improvement
67%reduction in latency
GEN AI
“Speed is key. By moving to the voyage-4-large model, our retrieval latency dropped from 300ms to 100ms across P50, P95, and P99. Voyage AI provides the accuracy and performance we need to deliver answers in under a second while the conversation is still happening.”
Aniket Patel
Founder, Tenali AI
Read Story

FAQ

Power your AI with best-in-class retrieval accuracy

Start building with Voyage AI to deliver the precision, scale, and freedom your next-generation applications and agents demand.
Get StartedExplore Voyage API
READY FOR PRODUCTION AI
  • State-of-the-art retrieval accuracy
  • Total cloud neutrality and portability
  • Available natively in MongoDB Atlas
  • Enterprise-grade security and compliance roadmap
  • Free tokens for new users