TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Companies
Voyage AI
Models
Voyage 4 large

Voyage 4 large

By Voyage AI
voyage-4-large is the flagship model in the Voyage 4 series, a family of text embedding models with a shared embedding space. It is the first production-grade embedding model to use a mixture-of-experts (MoE) architecture, enabling state-of-the-art retrieval accuracy at serving costs 40% lower than comparable dense models. Supports a 32K token context window and produces embeddings in 2048, 1024, 512, or 256 dimensions via Matryoshka learning. Multiple quantization formats are available: 32-bit float, signed/unsigned 8-bit integer, and binary precision. Optimized for general-purpose and multilingual retrieval, it is designed for semantic search, RAG pipelines, and context-engineered agents. Compatible with smaller Voyage 4 models for asymmetric retrieval, enabling cost-efficient deployments without re-vectorizing document corpora.
Text Gen 7
Released: January 15, 2026

Overview

voyage-4-large is a state-of-the-art general-purpose and multilingual text embedding model using a mixture-of-experts (MoE) architecture. It delivers frontier retrieval accuracy with serving costs 40% lower than comparable dense models. Features a 32K context window, flexible output dimensions (256, 512, 1024, 2048), and multiple quantization options including float, int8, uint8, binary, and ubinary.

🔗Embeds🔍Text classification

About Voyage AI

Voyage AI provides best-in-class embedding models and rerankers for search and retrieval over unstructured data, used to power retrieval-augmented generation (RAG) and AI applications. It offers general-purpose, domain-specific (finance, legal, code) and company-specific fine-tuned models. Founded in 2023 and based in Palo Alto, the company was acquired by MongoDB, Inc. in February 2025 and now operates as a MongoDB subsidiary.

Industry: Artificial Intelligence
Location: Palo Alto, California, US
Website: voyageai.com
View Company Profile

Related Models

Last updated: June 24, 2026
0 AIs selected
Clear selection
#
Name
Task