Skip to content
cohere/rerank-v4.0-fast

33K context · Dec 2025 · 2 upstreams

Cohere's Rerank 4.0 Fast is the low-latency Rerank 4 variant. It scores how relevant each document is to a query across 100+ languages. Use it as a second stage after vector or keyword search when latency matters more than the last bit of quality.

context
33K
input / 1M
$2.00
output / 1M
$0
routes
2
speed, 24h
—

Routes, in fallback orderThe first healthy route answers. Add a key to use a BYOK route.

2
  1. 1CoherePlatform · your credits$2.00 / $0–
  2. 2CohereYour key · not addedBYOK–

Try itOne message, one streamed reply

Uptime, last 48 hours

OKDegradedDown—

Details

Owner
Cohere
Kind
Rerank
Released
Dec 2025
Context
33K
Data policy
Provider retention
Endpoint
/api/v1/rerank

Quick start

Code

import osfrom openai import OpenAI client = OpenAI(    api_key=os.environ["ANYROUTER_API_KEY"],    base_url="https://anyrouter.dev/api/v1",) resp = client.chat.completions.create(    model="cohere/rerank-v4.0-fast",    messages=[{"role": "user", "content": "Say hi in 3 words."}],)print(resp.choices[0].message.content)
More details: pricing table, filters, performance, links

Upstreams and pricing

ProviderAccessStatusProvider details
Credits — billed by AnyRouter
2.000
Your own key (BYOK) — provider bills you, $0 AnyRouter fee
00

Which key answers this model

Your request → your own keys first (none added yet). The provider bills you; AnyRouter adds $0.

If none of your keys can serve it → the shared pool: keys other people donated. You pay the list price from AnyRouter credits, and the donor earns a reward.

Pool for this model: not covered yet.

Share cards
Rerank 4.0 Fast share card
Rerank 4.0 Fast
Cohere upstream share card
Cohere upstream
Cohere upstream share card
Cohere upstream