Rerank (Cohere-compatible)

Rerank documents against a query over x402 - the Cohere /rerank wire ({query, documents[], top_n} -> results with relevance_score), served by cohere/rerank-v3.5, $0.002 per call in USDC, no API key, no signup. Send POST /v1/rerank with the required fields query and documents and pay $0.002 per call over x402 or MPP (there is no free tier). It returns a JSON object with id, model, results and usage.

Up to 50 documents (1,600 chars each, 40k total) and a 500-char query per call. Deterministic, so a byte-identical repeat within 10 minutes is served FREE from cache (X-Cache: hit; opt out with cache:false). The retrieval companion to /v1/embeddings - embed and recall, then rerank the top candidates.

Category: LLM gateway · Tags: rerank reranking retrieval rag semantic-search cohere llm ai

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/v1/rerank \
  -H "Content-Type: application/json" \
  -d '{"query":"What is the capital of France?","documents":["Paris is the capital of France.","Berlin is the capital of Germany.","Madrid is in Spain."],"top_n":2}'

Without payment this returns HTTP 402 Payment Required with the exact price for v1-rerank; any x402 v2 or MPP client pays it and retries.

Example response

{
  "id": "gen-rerank-…",
  "model": "rerank-v3.5",
  "results": [
    {
      "index": 0,
      "relevance_score": 0.89,
      "document": {
        "text": "Paris is the capital of France."
      }
    },
    {
      "index": 1,
      "relevance_score": 0.15,
      "document": {
        "text": "Berlin is the capital of Germany."
      }
    }
  ],
  "usage": {
    "search_units": 1
  }
}

From an MCP client

catalog.call {
  "slug": "v1-rerank",
  "params": {
    "query": "What is the capital of France?",
    "documents": [
      "Paris is the capital of France.",
      "Berlin is the capital of Germany.",
      "Madrid is in Spain."
    ],
    "top_n": 2
  }
}

The hosted connector at https://agent402.tools/mcp needs a payment for v1-rerank; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.

Errors and behavior

• query and documents are required. An input the tool rejects returns an HTTP 4xx whose body carries error, tool, expected, required and example, so the caller can correct it.
• A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
• Wallet-only: this tool runs a model, so it has no proof-of-work tier. A prepaid card-credits key (Authorization: Bearer a402_...) also pays it.
• Model-backed: the answer is generated by a model, so the same input can produce different wording.
• A GET or HEAD to /v1/rerank returns the same 402 quote, so the price can be read without a body.
• An Idempotency-Key header makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB and a streamed response are not replayed).

Paid call (JavaScript agent)

import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/v1/rerank", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "query": "What is the capital of France?",
    "documents": [
      "Paris is the capital of France.",
      "Berlin is the capital of Germany.",
      "Madrid is in Spain."
    ],
    "top_n": 2
  }),
});

Related tools