- input
- $0.00
- output
- $0.00
- Context
- 32Ktokens
- Released
- 1mo ago
Cost/1M tokens
rerank-3-lite is a reranking model from Voyage AI, part of the Rerank 3 series and positioned as an upgrade from rerank-2.5. The maker says the series improves retrieval accuracy, with the largest gains on long documents and code, and that rerank-3-lite delivers faster, cheaper reranking than its counterpart rerank-3. It is built for teams creating search, RAG, and AI-agent applications.
How it compares
Frequently asked questions
API and pricing
Yes, VoyageAI by MongoDB lists a free endpoint with $0 input and output.
Yes. In the last day, 1 endpoint had uptime data and 1 was at 99% uptime or better, with the best uptime of 100.0% by VoyageAI by MongoDB.
Capabilities and specs
The context window is 32K tokens (32,000) and the maximum output is 29K tokens (28,800).
No. Its input modalities are text only, so it cannot read images, audio, video or PDFs.
Quality and benchmarks
Matched on model kind and release date with no comparable price, the closest alternatives are Rerank 5 Pro by Cohere, Rerank 5 Fast by Cohere, and Nemotron 3.5 Rerank 8B by NVIDIA.
Rerank 5 Prorerank-3-lite vs Rerank 5 ProRerank 5 Fastrerank-3-lite vs Rerank 5 FastNemotron 3.5 Rerank 8Brerank-3-lite vs Nemotron 3.5 Rerank 8B
Basics
rerank-3-lite was made by VoyageAI by MongoDB and released on September 29, 2026.
There are free API endpoints from VoyageAI by MongoDB, but the model's openness is unknown.
Generated from Vertical Tabs data, updated November 9, 2026.
Discussion
No comments yet
Be the first to share your thoughts.