TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Voyage lite 01

voyage-lite-01 is a lightweight text embedding model optimized for lower latency and cost compared to the full voyage-01 model. It transforms text into dense numerical vectors suited for retrieval-augmented generation (RAG), semantic search, and similarity tasks. The model uses a LlamaTokenizer and supports a context window of 4096 tokens. Available under an MIT license on Hugging Face and accessible via the Voyage AI API, it is now listed as a deprecated older model, succeeded by newer generations including voyage-3, voyage-3.5, and the voyage-4 series. It supports the same usage interface as voyage-01 through the Voyage AI Python SDK and REST API, with options for query and document input types to optimize retrieval performance.
Text Gen 7
Released: October 25, 2023

Overview

Lightweight text embedding model from Voyage AI for retrieval-augmented generation and semantic search. Converts text inputs into dense vector representations with a 4096-token context window. A smaller, faster variant of voyage-01, now deprecated and superseded by newer Voyage AI embedding generations. Available via API and as open weights under MIT license.

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
View Company Profile
Last updated: June 23, 2026
0 AIs selected
Clear selection
#
Name
Task