Rerank 5 Fast is Cohere's reranking model with a 33K context window and up to 33K output tokens, available from 2 providers, starting at $0.02 / 1M input. A low-latency multilingual reranking model that re-ranks English and non-English documents and semi-structured JSON data for faster retrieval pipelines.
Specifications
Canonical IDcohere-rerank-5-fast
TypeReranking
StatusActive
CreatorCohereCohere
Providers
Context Window33K tokens
Max Output33K tokens
Input ModalitiesText
Release Date · 13 days ago

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
Input
$ / 1M
Cohere logo
Cohere
rerank-v5.0-fast
$0.02
Vercel AI Gateway logo
Vercel AI Gateway
cohere/rerank-v5-fast
$0.02

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Rerank 5 Fast33K$0.020—Current
Rerank 5 Pro33K$0.050—Available
Rerank 4 Fast33K——Available
Rerank 4 Pro33K——Available
Semantic Ranker 4 Default————Available
Semantic Ranker 4 Fast————Available
Voyage Rerank 332K$0.050—Available
Voyage Rerank 3 Lite32K$0.020—Available
Rerank 3.54K——Deprecated
Voyage Rerank 3.532K——Available
NV RerankQA Mistral 3 4B————Available

Model IDs

cohere-rerank-5-fast
cohere/rerank-v5-fast
rerank-v5.0-fast