Rerank 4 Pro is Cohere's reranking model with a 33K context window and up to 33K output tokens, available from 2 providers. Cohere's fourth-generation pro-tier reranking model offering maximum accuracy for sorting documents by semantic similarity to a query.
Specifications
Canonical IDcohere-rerank-4-pro
TypeReranking
StatusActive
CreatorCohereCohere
Providers
Context Window33K tokens
Max Output33K tokens
Input ModalitiesText
Release Date · 11 months ago
Deprecation Date

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output0/5
Text·
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Query
$ / query
Azure AI Foundry logo
Azure AI Foundry
cohere:rerankv4pro
$0.0025
Cohere logo
Cohere
rerank-v4.0-pro
$0.0025

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Rerank 5 Pro33K$0.050—Available
Rerank 4 Pro33K——Current

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Rerank 5 Fast—33K$0.020—
Rerank 4 FastFast33K——
Semantic Ranker 4 Default—————
Semantic Ranker 4 FastFast————
Voyage Rerank 3—32K$0.050—
Voyage Rerank 3 Lite—32K$0.020—
Rerank 3.5—4K——
Voyage Rerank 3.5—32K——
NV RerankQA Mistral 3 4B—————
Rerank 3 English——4K——

Model IDs

azure_ai/cohere-rerank-v4.0-pro
cohere-rerank-4-pro
cohere-rerank-v4-0-pro
cohere/rerank-v4-pro
rerank-v4.0-pro