Cohere: Rerank v3.5

cohere/rerank-v3.5

Released Apr 5, 20264,096 context

$0/M input tokens$0/M output tokens

Rerank v3.5 is designed to reorder search results for improved relevance. It supports multi-aspect and semi-structured data reranking over 100+ languages. Ideal for refining results from semantic or keyword search pipelines.

Cohere: Rerank v3.5

cohere/rerank-v3.5

Released Apr 5, 20264,096 context

$0/M input tokens$0/M output tokens

Providers for Rerank v3.5

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Performance for Rerank v3.5

Compare different providers across OpenRouter

Effective Pricing for Rerank v3.5

Actual cost per million tokens across providers over the past hour

Apps using Rerank v3.5

Top public apps this month

Recent activity on Rerank v3.5

Total usage per day on OpenRouter

Prompt

Completion

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Uptime stats for Rerank v3.5

Uptime stats for Rerank v3.5 across all providers

Sample code and API for Rerank v3.5

OpenRouter normalizes requests and responses across providers for you.

OpenRouter provides a rerank API that reorders documents by relevance to a query. Pass a query and a list of documents, and the model returns them ranked by relevance score.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.