- input
- $0.00
- output
- $0.00
- Context
- 33Ktokens
- Listed
- 1w ago
Cost/1M tokens
Cohere Rerank 5 Fast is the lower-cost, speed-optimized tier of Cohere's Rerank 5, released as part of the company's latest generation of search models alongside Embed 5 and Parse 5. Cohere says the Fast tier reaches reranking quality close to its Pro tier at a lower cost, and its new Context Focus returns the most relevant passages within each document to reduce LLM token costs. The model is built for enterprise retrieval work, ranking passages for RAG pipelines and agent workflows in domains such as finance, healthcare, scientific research and multilingual search.
How it compares
Frequently asked questions
API and pricing
Yes, Cohere lists a free Rerank 5 Fast API endpoint with $0 input and output.
Yes. Last day, 1 endpoint had uptime data and 1 was at 99% uptime or better, with the best uptime at 100.0%, by Cohere.
Capabilities and specs
The context window of Rerank 5 Fast is 33K tokens (32,768), and its maximum output is 29K tokens (29,491).
No. Rerank 5 Fast only accepts text input and cannot read images, audio, video or PDFs.
Quality and benchmarks
The closest alternatives are rerank-3 by VoyageAI by MongoDB, rerank-3-lite by VoyageAI by MongoDB and Nemotron 3.5 Rerank 8B by NVIDIA. They were matched on model kind and release date, with no comparable price.
rerank-3Rerank 5 Fast vs rerank-3rerank-3-liteRerank 5 Fast vs rerank-3-liteNemotron 3.5 Rerank 8BRerank 5 Fast vs Nemotron 3.5 Rerank 8B
Versions and lineage
The listed specs are identical: both have a 33K token (32,768) context, cost $0.00 input and $0.00 output per 1M tokens, and were released November 3, 2026.
Basics
Rerank 5 Fast was made by Cohere. It was first listed on OpenRouter on November 3, 2026.
Yes, Cohere offers free API endpoints for Rerank 5 Fast. Its openness is unknown.
Generated from Vertical Tabs data, updated November 9, 2026.
Discussion
No comments yet
Be the first to share your thoughts.