Tools · SPBoucher
Menu

Voyage AI

by MongoDB (Voyage AI) · API service · also known as Voyage AI by MongoDB, voyageai

Hosted embedding and reranking models for retrieval, including code, finance, law and multimodal variants, offered by MongoDB with a free token allowance and pay-as-you-go API

ProprietaryFreemiumUsage-basedEnterpriseCloud
Visit official site Compare

Link verified Nov 2, 2026

Overview

Voyage AI provides embedding and reranking models as a hosted API and is now branded as part of MongoDB's data platform. The embedding endpoint converts text, code, images and video into dense vectors for semantic search and retrieval-augmented generation; the rerank endpoint scores query-document pairs to refine candidates from vector or lexical search. Current families include the voyage-4 text series in large, standard and lite sizes plus a context-focused variant, voyage-code for source code, voyage-finance and voyage-law for domain text, voyage-multimodal for mixed media and the rerank series. A Batch API processes large jobs at lower cost and a Files API stores inputs.

Access is through a REST API with an official Python client (MIT) and through cloud marketplaces such as AWS, including in-VPC deployment; the models are designed to work with any vector database, not only MongoDB Atlas. Pricing is a free token allowance per account followed by per-token (and per-pixel for images) billing, with fine-tuned models on dedicated instances arranged through sales. Voyage is a natural pairing for a retrieval stack that wants stronger domain embeddings than general-purpose providers, with the usual trade-off that embeddings are computed off-premises and tied to a vendor's model lifecycle.

Capabilities

  • Text embedding models in several sizes including a context-focused variant
  • Domain embeddings for code, finance and law
  • Multimodal embeddings for text, images and video
  • Rerankers for query-document relevance scoring
  • Batch API and Files API for large jobs
  • Python client and marketplace or in-VPC deployment

Typical workflows

  1. Embed a document corpus and store vectors in a database
  2. Rerank the top results of a hybrid search before passing them to an LLM
  3. Run a nightly batch embedding job over new filings

Strengths

  • Domain-specific and multimodal model lineup
  • Free allowance for prototyping
  • Vector-database agnostic

Limitations

  • Hosted only; data leaves your infrastructure
  • Model deprecations require re-embedding corpora
  • Fine-tuned and dedicated options go through sales

Prerequisites

  • Voyage AI API key
  • A vector store for the resulting embeddings

Who it is for

  • Teams building RAG over specialized corpora
  • Developers on MongoDB Atlas
  • Researchers needing finance or legal embeddings

Alternatives & comparison

  • Cohere

    Enterprise-focused model provider with Command generation, Embed and Rerank retrieval models, Aya multilingual research models, the North agent platform and private or dedicated deployment options

    ProprietaryFreemium
  • Gemini API

    Google's developer API for the Gemini model family, keyed from Google AI Studio, with function calling, Search grounding, Live API, image and video generation and a free tier

    ProprietaryFreemium
  • OpenAI API

    OpenAI's hosted developer platform: Responses and Chat Completions APIs, Realtime voice, embeddings, images, audio, fine-tuning, evals and managed agents

    ProprietaryUsage-based
  • Sentence Transformers

    Python library for computing and training embedding, cross-encoder reranker, sparse and multi-vector retrieval models, maintained by Hugging Face with thousands of pretrained models on the Hub

    Open sourceOpen source
Compare Voyage AI with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

  • Official documentation
    Voyage AI documentation

    https://docs.voyageai.com/docs/introduction

    Supports: capabilities

    checked Nov 1, 2026
  • Official site
    Voyage AI by MongoDB

    https://www.voyageai.com/

    Supports: name, vendor, summary

    checked Nov 1, 2026
  • Pricing page
    https://docs.voyageai.com/docs/pricing

    Supports: pricing_model, capabilities

    Free allowance then pay-as-you-go; lists voyage-4, code, finance, law, multimodal and rerank families

    checked Nov 1, 2026
  • Repository
    voyageai-python (MIT)

    https://github.com/voyage-ai/voyageai-python

    Supports: languages

    checked Nov 1, 2026
Confidence
High
Reviewed
Nov 1, 2026
Links
Verified · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

pgvector

Andrew Kane (pgvector project) · Vector databases

In-depth entry

PostgreSQL extension adding vector types, distance operators and HNSW/IVFFlat indexes for similarity search inside the database

PostgreSQLOpen sourceFreeSelf-hostedNov 2, 2026

Qdrant

Qdrant Solutions GmbH · Vector databases

In-depth entry

Open-source vector search engine written in Rust with filterable HNSW indexes, sparse and multi-vector support, REST/gRPC APIs and a managed cloud

Apache-2.0Open sourceFreemiumLocalSelf-hostedNov 2, 2026

LlamaIndex

LlamaIndex, Inc. · Agent frameworks & orchestration

Open-source Python framework for retrieval-augmented agents over your data, with connectors, indexes, query engines and event-driven workflows, alongside the commercial LlamaParse document platform

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

Weaviate

Weaviate B.V. · Vector databases

Open-source vector database in Go with pluggable vectorizer modules, hybrid BM25 and vector search, multi-tenancy and a managed cloud

BSD-3-ClauseOpen sourceFreemiumSelf-hostedBroken

Chroma

Chroma · Vector databases

Open-source embedding database with a minimal Python and JavaScript API, usable in-process, as a server or through Chroma Cloud

Apache-2.0Open sourceUsage-basedLocalSelf-hostedNov 2, 2026

Pinecone

Pinecone Systems, Inc. · Vector databases

Fully managed, proprietary vector database service with serverless indexes, namespaces, metadata filtering and integrated embedding and reranking

ProprietaryFreemiumUsage-basedNov 2, 2026