Grounded chat (web search, OpenAI-compatible)

OpenAI-compatible chat completions GROUNDED in a live web search on every call: the gateway runs an Exa search (up to 5 results) for the prompt, hands the results to the model, and returns the answer with url_citation annotations - $0.03 per call in USDC, no API key, no signup. Send POST /v1/grounded/chat/completions with the required field messages and pay $0.03 per call over x402 or MPP (there is no free tier). It returns a JSON object with id, object, created, model, choices and 2 more.

Model is chosen server-side like the auto tier (omit "model" or send "auto"; explicit ranked models accepted); the response adds agent402_router {category, quality, served}. The sanctioned way to get live-web answers from the gateway (":online" model variants are refused elsewhere). Caps 16k chars in / 1024 tokens out. Streaming supported. Never cached - the web moves.

Category: LLM gateway · Tags: llm ai inference chat gateway openai-compatible openrouter router

TRY IN PLAYGROUND →

Parameters

Example request

curl -i -X POST https://agent402.tools/v1/grounded/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"What is the current Node.js LTS version? One line, cite the source."}],"max_tokens":120}'

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

Example response

{
  "id": "gen-…",
  "object": "chat.completion",
  "created": 1750000000,
  "model": "openai/gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 1,
    "total_tokens": 13
  },
  "agent402_router": {
    "category": "general",
    "quality": "balanced",
    "served": "openai/gpt-4o-mini"
  }
}

From an MCP client

catalog.call {
  "slug": "v1-chat-grounded",
  "params": {
    "messages": [
      {
        "role": "user",
        "content": "What is the current Node.js LTS version? One line, cite the source."
      }
    ],
    "max_tokens": 120
  }
}

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

Errors and behavior

• messages is 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/grounded/chat/completions 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/grounded/chat/completions", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "messages": [
      {
        "role": "user",
        "content": "What is the current Node.js LTS version? One line, cite the source."
      }
    ],
    "max_tokens": 120
  }),
});

Related tools