Enterprise DNAEnterprise DNA
LModels
Cohere logo

Cohere Rerank 3.5

by Cohere

Reranking model for improving retrieval quality in search and recommendation systems

Visit CohereSubmit your build →
CR

Models

Cohere Rerank 3.5

Added 13 July 2026

#cohere#temperature

Overview

Reranking model for improving retrieval quality in search and recommendation systems

Best for

Best for
Search-result reranking

How to use / API access

Call via other with model id `cohere/rerank-v3.5`.

  • other · cohere/rerank-v3.5

OpenRouter id: cohere/rerank-v3.5

Notes

Cohere Rerank 3.5 is listed in the EDNA Models directory, sourced from models.dev.

Pros

  • Reordering an existing candidate result set
  • text input; rerank output on the listed OpenRouter route

Cons

  • Expecting reranking to discover documents outside its candidates
  • Treating relevance scores as calibrated truth probabilities
  • This route produces non-text output or rerank results. Listed text-token rates are not a complete workload price; zero text-token rates do not mean free generation. Verify the route-specific billing unit before estimating cost.
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Cohere Rerank 3.5.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-20. Hosting routes and app features can differ.

DeveloperCohere
Exact model identifiercohere/rerank-v3.5
Inputtext
Outputrerank
Tool calling
Not established
Structured output
Not established
Reasoning controls
Not established
Availability
available
Price basis
unknown
Licence verification
Check the developer licence; the model name is insufficient

This route produces non-text output or rerank results. Listed text-token rates are not a complete workload price; zero text-token rates do not mean free generation. Verify the route-specific billing unit before estimating cost.

Consider it for

  • Reordering an existing candidate result set
  • Ranking semi-structured records for a specific query

Watch for

  • Expecting reranking to discover documents outside its candidates
  • Treating relevance scores as calibrated truth probabilities

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Query: refundable annual subscription. Rank A annual plan refundable within 14 days, B monthly plan non-refundable, C annual plan no refunds. Return candidate IDs and scores only.

Check the result: A should outrank the two policy mismatches; all outputs must reference supplied IDs.

Compare another approach

Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

cohere/rerank-v3.5: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-20
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Understand the capabilitiesRead the model guide ↗

Check the source

This route uses unknown pricing. A token calculator is not a quote for this model. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Compare this model with alternatives →