Cohere Rerank 3.5 (New)

The cohere.rerank.3-5 model takes in a query and a list of texts and produces an ordered array with each text assigned a relevance score. The relevance score is how the model ranks the documents, that's, how well each text matches the query.

Available in These Regions

Brazil East (Sao Paulo) (dedicated AI cluster only)
Germany Central (Frankfurt) (dedicated AI cluster only)
Japan Central (Osaka) (dedicated AI cluster only)
Saudi Arabia Central (Riyadh) (dedicated AI cluster only)
UK South (London) (dedicated AI cluster only)
US East (Ashburn) (dedicated AI cluster only)
US Midwest (Chicago) (dedicated AI cluster only)

Access this Model

Access this model through the Console, API, and the CLI:

Key Features

Dedicated mode only.
Not available on-demand or in the playground.
Access the model that's hosted on a cluster through API and SDK.
For dedicated mode, create an endpoint on a hosting dedicated AI cluster, host the model on the cluster, and then run the RerankText API or its relevant SDK.

Dedicated AI Cluster for the Model

To reach a model through a dedicated AI cluster in any listed region, you must create an endpoint for that model on a dedicated AI cluster. For the cluster unit size that matches this model, see the following table.


Base Model	Fine-Tuning Cluster	Hosting Cluster	Pricing Page Information	Request Cluster Limit Increase
Model Name: Cohere Rerank 3.5 OCI Model Name: `cohere.rerank.3-5`	Not available for fine-tuning	Unit Size: RERANK_COHERE Required Units: 1	Pricing Page Product Name: Cohere Rerank - Dedicated	Limit Name: `dedicated-unit-rerank-cohere-count` For Hosting, Request Limit Increase by: 1

Tip

If you don't have enough cluster limits in your tenancy for hosting the Cohere Rerank 3.5 model on a dedicated AI cluster, request the dedicated-unit-rerank-cohere-count limit to increase by 1.

Endpoint Rules for Clusters

A dedicated AI cluster can hold up to 50 endpoints.
Use these endpoints to create aliases that all point either to the same base model or to the same version of a custom model, but not both types.
Several endpoints for the same model make it easy to assign them to different users or purposes.


Hosting Cluster Unit Size	Endpoint Rules
RERANK_COHERE	Base model: To run the `cohere.rerank.3-5` model on several endpoints, create as many endpoints as you need on a RERANK_COHERE cluster (unit‑size). Custom model: You can't fine‑tune `cohere.rerank.3-5`, so you can't create and host custom models built from that base.

Tip

To increase the call volume supported by a hosting cluster, increase its instance count by editing the dedicated AI cluster. See Updating a Dedicated AI Cluster.
For more than 50 endpoints per cluster, request an increase for the limit, endpoint-per-dedicated-unit-count. See Requesting a Service Limit Increase and Service Limits for Generative AI.

Cluster Performance Benchmarks

Review the Cohere Rerank 3.5 cluster performance benchmarks for different scenarios.

Release and Retirement Dates


Model	Release Date	On-Demand Retirement Date	Dedicated Mode Retirement Date
`cohere.rerank.3-5`	2025-05-14	On-demand mode isn't available for this model.	At least 6 months after the release of the 1^st replacement model.

Important

For a list of all model time lines and retirement details, see Retiring the Models.

Rerank Model Parameter

For the Rerank model parameters, see the RerankText API documentation.

Oracle Cloud Infrastructure Documentation