Cohere: Rerank 4 Fast - API for Egypt, billed in EGP

Live
coherererank-4-fast

Cohere's AI search foundation model for enhancing the relevance of information surfaced within search and RAG systems.

Modality

Rerank

Context window

33K tokens

Max output

29K tokens

Region

US

Published

27 Oct 2026

Pricing

Price

0.135 EGP per search

The provider reports the exact charge on every response.

  • 0.135 EGP per search: one query with up to 100 documents; a document longer than 500 tokens together with the query counts as more than one.
  • The exact charge is reported by the provider on every response and is what you pay.

Use it via the API

Run inference

POST /v1/rerank — Cohere-compatible rerank: call it over HTTP; the OpenAI SDKs have no method for it.

Rerank guide ↗
import httpx

response = httpx.post(
    "https://backend.sovereigneg.com/v1/rerank",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "rerank-4-fast",
        "query": "What is the capital of Egypt?",
        "documents": [
            "Paris is the capital of France.",
            "Cairo is the capital of Egypt.",
            "Madrid is the capital of Spain.",
        ],
        "top_n": 3,
    },
    timeout=30,
)
print(response.json())

Frequently asked questions

What is the context window of Cohere: Rerank 4 Fast?

Cohere: Rerank 4 Fast supports a context window of 32,768 tokens (33K).

Where is Cohere: Rerank 4 Fast hosted?

Cohere: Rerank 4 Fast is served from US (US-hosted inference).

Cohere: Rerank 4 Fast API Price in Egypt (EGP) | SovereignEG