Rerank 4 Pro

by CohereRerank

Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems. Features a 32K context window, multilingual support across 100+ languages, no data pre-processing...

Context: 32.8K tokens
Max output: 29,491 tokens
Released: 2026-04-06
Weights: unknown

Feed

cohere/rerank-4-pro

Specifications

Full facts as recorded, incl. what is unknown.

Released: 2026-04-06
Weights: unknown
Input: Text
Output: Rerank
Context window: 32,768 max across endpoints
Max output: 29,491
Providers: 0 + 1 gateway, not counted as providers
Epoch Capabilities Index: not evaluated
Direct price range: no comparable direct price

More details

Last updated: —
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

Tool callingunknown
Parallel toolsunknown
Structured outputunknown
Reasoningunknown
Image inputunknown
PDF inputunknown
Audio inputunknown
Audio outputunknown
Video inputunknown
Prompt cachingunknown
Web searchunknown
Computer useunknown
System messagesunknown
Assistant prefillunknown
Temperatureunknown
Streamingunknown
Attachmentsunknown

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from Cohere

Newest Cohere models in the catalogue. All Cohere models

Model	Released	Context	Listed price
Embed 5 Pro	2026-09-30	128K	from $0.12 /1M tok
Embed 5 Fast	2026-09-30	128K	from $0.08 /1M tok
North Small Translate	2026-09-09	32.8K	unpriced
North Mini Code	2026-06-17	256K	unpriced
North Mini Code	2026-06-09	256K	unpriced
Command A Plus	2026-05-20	128K	from $2.50 /1M tok
Tiny Aya Fire	2026-02-17	8K	unpriced
Tiny Aya Earth	2026-02-17	8K	unpriced

Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model