We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
cohere/rerank-5-proRuns on your balance at the prices above. New accounts start with free usage.
Settings
Cohere: Rerank 5 Pro is a reranking model from Cohere, positioned as the higher-accuracy tier of the company's Rerank 5 family. Rather than generating text, it scores and reorders candidate documents against a query, which places it in the retrieval stage of a search or question-answering pipeline. It is made for developers who already have a set of candidate passages and need them sorted by relevance before they reach a downstream step.
The model works with text input and produces reranking output. It accepts up to 32,768 tokens of context, and its maximum output is 29,491. Because its output is a reranking rather than prose, you should think of it as a scoring and ordering component rather than a chat or completion model. It does not take image or audio input, and it does not generate written answers on its own.
The practical uses follow directly from that shape. A common pattern is a two stage retrieval setup: a fast vector or keyword search returns a broad set of candidates, and Rerank 5 Pro reorders them so the most relevant documents sit at the top. That helps retrieval augmented generation pipelines, where the quality of the passages passed to a generator matters more than the size of the candidate pool. It also fits enterprise search, documentation lookup, and any workflow where you need to rank existing text against a query rather than create new text. Because the higher-accuracy tier targets precision, it suits cases where ordering quality is the priority.
You call the model through api14's OpenAI-compatible API using the model id "cohere/rerank-5-pro". The supported parameters list is empty, so you should not expect tunable request options beyond what the endpoint accepts by default. Send your query and candidate documents in the request and read back the reranked results. If you are already using an OpenAI-compatible client, you can point it at api14 and swap in this model id without changing your overall integration approach.
One thing to weigh is scope. This model only reranks text, so if your task is generating answers, summarizing, or handling non-text inputs, a different model will fit better. It is also a reranking step rather than a standalone retrieval system, so you still need something upstream to produce the candidate documents. Within those boundaries, it is a focused tool for improving the order in which text reaches the rest of your pipeline.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.post("/rerank", { body: {
"model": "cohere/rerank-5-pro",
"query": "What is the capital of France?",
"documents": [
"Paris is the capital of France.",
"Berlin is in Germany."
],
"top_n": 1
} });
console.log(result.results);
This community has no topics yet. Open the first one about Cohere: Rerank 5 Pro.