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

Voyage

By Voyage AI
voyage (voyage-01) is a general-purpose text embedding model developed by Voyage AI for retrieval-augmented generation (RAG) and semantic search. It produces dense vector embeddings capturing semantic content of text, enabling high-accuracy document retrieval. At launch, voyage-01 outperformed OpenAI text-embedding models by more than 5 points on the Massive Text Embeddings Benchmark (MTEB) and demonstrated superior results across nine custom real-world industry domain datasets. Built on a LlamaTokenizer architecture with a 4,096-token context window. Accessible through the Voyage AI API, it supports retrieval, semantic similarity, and RAG pipeline integration. The Hugging Face repository contains only the tokenizer files, not model weights. This is the original generation in Voyage AI's embedding model lineup, predating the voyage-2, voyage-3, and voyage-4 series.
Text Gen 7
Released: October 29, 2023

Overview

voyage is a text embedding model that converts text into dense vector representations for semantic retrieval. Originally released as voyage-01 via the Voyage AI API, this Hugging Face repository contains only the tokenizer (MIT licensed). Built on a LlamaTokenizer architecture with a 4,096-token context window, designed to outperform OpenAI text embeddings on retrieval benchmarks.

🔗Embeds🔍Information retrieval📚Knowledge bases🔍Semantic content 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

  • Gen 7
    Gemini Pro
    Gemini Pro is the balanced general-use tier of Google’s original Gemini 1.0 family.
    Text
    Released 2y ago
  • Gen 7
    Command A Reasoning
    Command A Reasoning is Cohere’s first dedicated reasoning model: 111B parameters, 256K context, 32K output, and a switchable “thinking” mode. It’s built for tool use, RAG, agent workflows, and multilingual tasks (23 languages), and can run on 1–2 A100/H100 GPUs.
    Text
    Released 10mo ago
  • Gen 1
    HyperCLOVA
    Korean language model with 82B parameters.
    Text
    Released 4y ago
Last updated: June 23, 2026
0 AIs selected
Clear selection
#
Name
Task