Skip to content
AI Atlas
ModelActivefamily · Rerank

rerank-v4.0-fast

Coheredocs.cohere.com/docs/models

A light version of rerank-v4.0-pro, this is a multilingual model that allows for re-ranking English and non-english documents and semi-structured data (JSON). This model is better suited for low latency and high throughput use-cases than its pro variant.

Updated 13 min ago · first seen 11 Sept 2026

model_01M294H98R6Y3741NXG3SKJ9NH

Context
32K tokens
T1 · 13 min ago

Specification

Family
Rerank

Source:Cohere — docs & blogT1observed 13 min agohigh

Context window
32K tokens

Source:Cohere — docs & blogT1observed 13 min agohigh

Modalities
text

Source:Cohere — docs & blogT1observed 13 min agohigh

Input modalities
text

Source:Cohere — docs & blogT1observed 13 min agohigh

API model id
rerank-v4.0-fast

Source:Cohere — docs & blogT1observed 13 min agohigh

Official page

Source:Cohere — docs & blogT1observed 13 min agohigh

Endpoints
Rerank

Source:Cohere — docs & blogT1observed 13 min agohigh

Foundry model id
cohere-rerank-v4-fast

Source:Cohere — docs & blogT1observed 13 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

10

Source tiers

T110

Freshest observation

13 min ago

Conflicts

None