TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Companies
Voyage AI
Models
Voyage 3 large

Voyage 3 large

By Voyage AI
voyage-3-large is a general-purpose text embedding model built for semantic retrieval across diverse domains including law, finance, code, technical documentation, and multilingual content spanning 26 languages. It supports a 32K-token context window and four output dimensions (256, 512, 1024, 2048), enabled by Matryoshka representation learning. Multiple quantization formats are supported (float32, int8, uint8, binary, ubinary), allowing large reductions in vector storage costs with minimal retrieval quality loss. Binary rescoring is supported for further accuracy gains on top of binary retrieval. It ranks first across 100 evaluation datasets spanning eight domains and is designed for retrieval-augmented generation, semantic search, and similarity tasks where precision and dimensionality tradeoffs matter.
Text Gen 7
Released: January 7, 2025

Overview

Text embedding model optimized for general-purpose and multilingual retrieval across law, finance, code, and long-document domains. Supports a 32K-token context window, flexible output dimensions (256, 512, 1024, 2048), and multiple quantization formats (float32, int8, uint8, binary) via Matryoshka and quantization-aware training. Accessed via API.

🔎Semantic search🔍Information retrieval📄Document analysis

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 23, 2026
0 AIs selected
Clear selection
#
Name
Task