Skip to content

Model detail

Rerank v4.0 Pro

Provided by Cohere
Pay-as-you-go Dynamic pricing

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 required, and state of the art performance with low latency.

Model specs

Model ID
rerank-v4.0-pro
Context length
32K
Max output
–
I/O modalities
Released
2026-04

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Tiered pricing

Unit: /1K searches

Pricing updated

Tier Search units /1K searches
base $2.5000

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Reranking

Rerank v4.0 Pro is Cohere's reranking model for second-stage ranking of retrieved passages. It accepts text input and returns ranked results. Rerank one query with your own documents before you wire it in.

What should you check before using it?

32,768 tokens across query and documents

Rerank v4.0 Pro handles up to 32,768 tokens across the query and its documents in one request. Size your query and document set against that window.

Why use it through MixRoute?

Call this model with a MixRoute API key

Use /v1/rerank with model ID rerank-v4.0-pro through MixRoute at https://api.mixroute.ai. Configure a client for this endpoint, then test the integration with a sample request before sending production traffic.

09

FAQ

Before switching production traffic to Rerank v4.0 Pro, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.