Rerank

Order a list of documents by relevance to a query. Rerankers are the second stage of a search pipeline: retrieve 50–200 candidates with embeddings or keyword search, then rerank and keep the top few for your prompt.

POST https://api14.com/api/v1/rerank

The official OpenAI SDKs have no rerank method, so call it with plain HTTP (every language example below does).

Request

Example

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-v3.5",
  "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);

curl https://api14.com/api/v1/rerank \
  -H "Authorization: Bearer sk-api14-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "cohere/rerank-v3.5",
    "query": "How do I reset my password?",
    "documents": [
      "Billing happens on the first of each month.",
      "To reset your password, open Settings and choose Security.",
      "Our office is closed on public holidays."
    ],
    "top_n": 2
  }'

Response

{
  "id": "gen-1791100000-rr1",
  "model": "cohere/rerank-v3.5",
  "results": [
    { "index": 1, "relevance_score": 0.94 },
    { "index": 0, "relevance_score": 0.08 }
  ],
  "usage": { "search_units": 1, "cost": 0.002 }
}

index points into your documents array. Results are sorted by relevance_score, highest first.

Pricing

Rerank models are billed per search at the model's listed price, displayed as "$ / 1K searches". The cost is in usage.cost and debited from your USD balance.

Listing rerank models

curl "https://api14.com/api/v1/models?category=rerank"

Errors

See Errors.