Wispr Flow - Don’t type, just speak
Mini toolsVoyage 3 lite
By Voyage AI
voyage-3-lite is a lightweight general-purpose text embedding model designed for semantic search, retrieval-augmented generation (RAG), and classification tasks where latency and cost efficiency are priorities. It produces 512-dimensional dense vector embeddings and supports a 32K-token context window, 4x larger than OpenAI embedding models. It achieves an NDCG@10 score of 72.98, outperforming OpenAI v3 large by 3.82% across eight evaluated domains including code, law, finance, technical documentation, long-context, and multilingual content. It also outperforms OpenAI v3 small by 7.58% at the same price point. The model supports 26 languages including French, German, Japanese, Spanish, Korean, Bengali, Portuguese, and Russian. It was developed using an improved architecture, distillation from larger models, over 2 trillion high-quality pre-training tokens, and retrieval result alignment via human feedback. Accessible via the Voyage AI API and Python and TypeScript SDKs.
Text
Gen 7
Overview
Lightweight general-purpose text embedding model optimized for latency and cost. Generates 512-dimensional vector embeddings with a 32K-token context window. Outperforms OpenAI v3 large by 3.82% on average retrieval accuracy across eight domains while costing 6.5x less, at $0.02 per 1M tokens.
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.
View Company Profile
Last updated: June 23, 2026
