Wispr Flow - Don’t type, just speak
Mini toolsvoyage lite 02 instruct
At launch it ranked #3 on the MTEB leaderboard, while being approximately 6x smaller in parameter count and 4x smaller in embedding dimensions than the other top-5 models — well-suited for production deployments where latency and cost matter.
Key features:
- 4,096-token context window
- Instruction-tuned for task-specific optimization
- Optimized for semantic search, RAG pipelines, text classification, and clustering
- Available via the Voyage AI API and integrated with platforms such as Pinecone
The 'lite' designation indicates it is the smaller, faster variant of the second-generation voyage-02-instruct family.
Overview
voyage-lite-02-instruct is a lightweight instruction-tuned text embedding model from Voyage AI's second generation. Ranked #3 on MTEB at launch, it achieves top-tier accuracy with 6x fewer parameters and 4x smaller embedding dimensions than other top-5 models. Supports a 4,096-token context window and task-specific instruction prefixes to boost performance across retrieval, classification, and semantic search.
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
