---
title: "Rerank v4.0 Pro"
route_path: "/model/rerank-v4.0-pro"
canonical_url: "https://www.pipellm.ai/model/rerank-v4.0-pro"
markdown_path: "/llms/models/rerank-v4.0-pro.md"
markdown_url: "https://www.pipellm.ai/llms/models/rerank-v4.0-pro.md"
content_type: "model-detail-page"
description: "Machine-readable detail page for Rerank v4.0 Pro."
generated_at: "2026-10-04T01:10:16.870Z"
---
Canonical page: https://www.pipellm.ai/model/rerank-v4.0-pro
Markdown mirror: https://www.pipellm.ai/llms/models/rerank-v4.0-pro.md
Content type: model-detail-page
Generated at: 2026-10-04T01:10:16.870Z
# Rerank v4.0 Pro
## Query Intents
- Understand pricing, provider availability, context window, and capabilities for Rerank v4.0 Pro.
- Compare Rerank v4.0 Pro against other models available through PipeLLM.
- Find the canonical model identifier to use in SDK or API requests.
## Overview
Rerank v4.0 Pro provides document reranking through PipeLLM. Use model ID rerank-v4.0-pro with /v2/rerank.
## Model Metadata
- Display name: Rerank v4.0 Pro
- Model ID: rerank-v4.0-pro
- Provider family: Cohere
- Release date: Unknown
- Context window: —
- Max output: —
- Input modalities: text
- Output modalities: text
- Tool use support: No
- Computer use support: No
- Cache control support: No
## Pricing (USD)
$0.0025 / request
## API Integration
Use the native API; protocol conversion is not supported.
- [Native HTTP](https://docs.pipellm.ai/api-reference/introduction): `/v2/rerank`
## Provider Availability
| Provider | Price (USD) | API |
| --- | --- | --- |
| Cohere | $0.0025 / request | /v2/rerank |

## Documentation
Send an authenticated POST request to https://api.pipellm.ai/v2/rerank with model set to rerank-v4.0-pro. Use the Cohere rerank request format with query and documents.