Seminal AI
§1

Rerank 4 Fast

The throughput/latency variant of Rerank 4 with the same 32K context — the right default for reranking in a live search path.

Data checked 2026-09-06

Cohere ga rerank-v4.0-fast

Context window
32K tokens in
Max output
Input
per 1M tokens
Output
per 1M tokens
Licence
proprietary

A What it is for

Priced per search, not per token: $2.00 per 1,000 searches (one search = one query against up to 100 documents); $5.00/hr Medium on Model Vault.

B Capabilities

Not documented.
Input modalitiestext
Output modalitiestext

C Others from Cohere

Model Context Max out In $/M Out $/M Blended Status
Command A+ command-a-plus-05-2026 128K 64K $0.00 $0.00 $0.00 ga open
Command A command-a-03-2025 256K 8K ga open
Command A Reasoning command-a-reasoning-08-2025 256K 32K ga open
Command A Translate command-a-translate-08-2025 8K 8K ga open
Command A Vision command-a-vision-07-2025 128K 8K ga open
Command R+ (08-2024) command-r-plus-08-2024 128K 4K $2.50 $10.00 $4.38 ga open
Command R (08-2024) command-r-08-2024 128K 4K $0.15 $0.60 $0.26 ga open
Command R7B command-r7b-12-2024 128K 4K $0.04 $0.15 $0.07 ga open
Command R (03-2024) command-r-03-2024 128K 4K $0.50 $1.50 $0.75 deprecated open
Command R+ (04-2024) command-r-plus-04-2024 128K 4K $3.00 $15.00 $6.00 deprecated open
Command command 4K 4K $1.00 $2.00 $1.25 deprecated
Command Light command-light 4K 4K $0.30 $0.60 $0.38 deprecated

D Verify before you commit

Model pricing changes without notice and this page is a snapshot. Confirm against the vendor's own page before you build a budget on it.

Source: cohere.com · checked 2026-09-06 · Cohere pricing · API docs