Cohere Rerank 5 launches in Pro and Fast tiers with 32K context; Pro scores 82.2 on BRIGHT
Cohere has released Rerank 5 in Pro and Fast tiers with a 32K context window, Context Focus passage extraction and calibrated relevance scores. Pro scores 82.2 on BRIGHT and costs $0.05 per 1M tokens.
Cohere Rerank 5 — Quick Specs
Cohere Rerank 5 ships in Pro and Fast tiers with a 32K context window, Context Focus passage extraction and calibrated relevance scores, according to a MarkTechPost report published October 22, 2026.
Key specifications
- Tiers: Pro and Fast
- Context window: 32K
- New features: Context Focus passage extraction and calibrated relevance scores
- Pro benchmark: 82.2 on BRIGHT
- Pro pricing: $0.05 per 1M tokens
Pricing for the Fast tier is not yet disclosed, and no other benchmark scores, parameter count or training cutoff date have been published in the report.
What is new
Rerank 5 adds two named capabilities. Context Focus provides passage-level extraction, and the model also returns calibrated relevance scores. The report describes both as part of the release alongside the two-tier structure.
What this means
Rerank 5 is Cohere's retrieval-stage model, offered in two tiers, so buyers choose between Pro and Fast. The 82.2 BRIGHT score applies to Pro only, and the $0.05 per 1M tokens price is reported for Pro. Teams comparing the two tiers cannot yet set Fast against Pro on benchmark or price. Context Focus and calibrated scores are the features that distinguish this release from a plain context-window upgrade.
Related Articles
NVIDIA releases Nemotron 3.5 Embed 8B, scoring 61.17 nDCG@10 on ViDoRe v3.1 among dense retrievers
NVIDIA has released Nemotron 3.5 Embed (8B BF16, 1B BF16, 1B NVFP4), Nemotron 3.5 Rerank 8B BF16 and Nemotron 3.5 Parse (631M parameters) as open, commercially available models. NVIDIA reports that the 8B embedder ranks first among dense retrievers on ViDoRe v3.1 with 61.17 nDCG@10, and that adding the reranker cuts agent token cost per query by roughly 13-14%.
Gradium open-sources Phonon 31m, a 31M-parameter on-device TTS model under Apache 2.0
Gradium has open-sourced Phonon, a family of on-device text-to-speech models. The English Phonon 31m has 31M parameters, ships under Apache 2.0, fits in 64.5 MB, and starts speaking in about 7 ms on a laptop CPU.
Hugging Face releases Carbon-X, a 14B-parameter open model that answers natural-language questions about DNA
Hugging Face released Carbon-X, a 14-billion-parameter open model that takes DNA sequences and English questions and returns conversational answers. It was trained on 300 billion tokens and is designed to run locally. Its developers say it has not yet been validated with wet lab experiments.
Ant Digital Technologies releases LingDT-Decision-1.0 in 4B and 27B sizes for direct structured decisions
Ant Digital Technologies has released LingDT-Decision-1.0, a model that makes structured choices directly instead of generating text. It comes in 4B and 27B sizes, and the company says it cuts token use by more than 90%.
Comments
Loading...