What it is:The Voyage 4 series is a new generation of text embedding models consisting of voyage-4-large, voyage-4, voyage-4-lite, and the open-weights voyage-4-nano. All models in the series share a compatible embedding space, eliminating the constraint of using the same embedding model at both document indexing and query time. Users can index with voyage-4-large for maximum retrieval quality, then query with any Voyage 4 model to optimize quality-latency-cost tradeoffs per use case.Who it’s for: These new models are designed to serve teams seeking even more accurate retrieval, as well as the new wave of AI developers building context-engineered agents and AI systems with long-term memory.Why it matters: Previous generations of embedding models required using identical models to embed both queries and documents. By sharing embedding spaces between models, the Voyage 4 model series enables flexibility in the way embeddings are generated: for example, using voyage-4-large for document/chunk embeddings and voyage-4-lite for query embeddings.How to get started:Sign up, generate a model API key, and get 200M free tokens on our latest models. Dive into the documentation and start building with the quick start.

What it is:The Embedding and Reranking API is a new serverless API service that provides developers with direct access to Voyage AI’s frontier retrieval models natively within the MongoDB Atlas platform. This service is database-agnostic, meaning it can be integrated into any tech stack or database, and features flexible, token-based pricing.Who it’s for: This API is designed for AI developers and teams building retrieval-powered AI systems, from semantic search and RAG (Retrieval-Augmented Generation) to AI agents. Whether you're an AI startup or an enterprise organization, this API simplifies your development workflow by consolidating critical retrieval components needed for building AI retrieval on a single platform.Why it matters: As AI systems become integral to everyday processes and products, they need high-quality context to reduce hallucinations. Voyage AI's models deliver industry-leading retrieval accuracy to meet this need. By offering these models within Atlas, MongoDB provides a unified platform for your entire AI retrieval stack, combining your operational database, vector search, and retrieval models under a single control plane with unified monitoring and billing. This reduces operational overhead while delivering the security and scalability of MongoDB Atlas.How to get started:Sign up, generate a model API key, and get 200M free tokens on each of our latest models. Dive into the documentation and start building with the Embedding and Reranking API on MongoDB Atlas.

What it is: Automated text embedding allows MongoDB Community users to create vector search indexes that automatically generate, store, and query text embeddings using Voyage AI models. This feature eliminates the need for manual embedding pipelines by managing the transformation of documents into vectors directly through a new autoEmbed field type in vectorSearch index definitions. Use with your favorite MongoDB language drivers, AI frameworks like LangChain and LangGraph, and the MongoDB MCP server.Who it’s for: This is for MongoDB Community Edition developers who want to implement semantic search but lack the specialized machine learning infrastructure to manage external embedding generation. It specifically serves teams looking to rapidly build AI-native applications or migrate to the latest embedding models with minimal integration complexity.Why it matters: The integration simplifies the developer workflow by replacing a multi-step, error-prone manual process with a single-click experience for semantic search. By handling vector synchronization and query embedding automatically, the product reduces maintenance overhead and accelerates the time to market for local and on-premises AI applications.How to get started:Automated Embedding in MongoDB Vector Search in Community Edition is available now, with MongoDB Atlas and MongoDB Vector Search in Enterprise Edition access coming soon. Jump in with our quick start guide.