cohere logo
cohere

Cohere: Rerank 4 Pro

Source description (English)

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...

Overview

Model specifications

Context
32,768 tokens
Maximum output
29,491 tokens
Architecture
text->rerank
Tokenizer
Cohere
Knowledge cutoff
Not provided
Moderated
Yes
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Search units
$0.0025
per search
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/rerank \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"cohere/rerank-4-pro","query":"What is the capital of France?","documents":["Paris is the capital of France.","Berlin is the capital of Germany."],"top_n":1}'
Capabilities

InputOutput

Input
text
Output
rerank
API

Supported API parameters

Available providers

1 Provider

Checked: September 16, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Cohere

Not provided
Context
33K
Maximum output
29K
cohere

4 models

All models