VoyageAI by MongoDB: rerank-2.5-lite - API for Egypt, billed in EGP

Live
voyageairerank-2.5-lite

rerank-2.5-lite is a reranker optimized for both latency and quality, delivering a 7.16% improvement in retrieval accuracy over Cohere Rerank v3.5 across 93 datasets.

Modality

Rerank

Context window

32K tokens

Max output

29K tokens

Region

US

Published

27 Oct 2026

Pricing

Input

1.24

EGP per 1M tokens

Output

—

EGP per 1M tokens

Monthly cost example

61.89 EGP

Illustrative estimate: 50M input + 15M output tokens per month at this model’s catalog rates.

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-2.5-lite",
        "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 VoyageAI by MongoDB: rerank-2.5-lite?

VoyageAI by MongoDB: rerank-2.5-lite supports a context window of 32,000 tokens (32K).

Where is VoyageAI by MongoDB: rerank-2.5-lite hosted?

VoyageAI by MongoDB: rerank-2.5-lite is served from US (US-hosted inference).

VoyageAI by MongoDB: rerank-2.5-lite API Price in Egypt (EGP) | SovereignEG