Chat completions — auto tier (eval-ranked routing)

OpenAI-compatible chat completions with server-side model choice: omit "model" (or send "auto") and the gateway routes the prompt to the top-ranked budget model for its task type (code / reasoning / long-context / general) from a fixed eval-derived ranking — deterministic, no LLM in the routing path. Provider errors fail over down the ranking automatically; the response adds agent402_router {category, served} alongside the standard model field. $0.01 per call in USDC over x402, caps 16k chars in / 1024 tokens out. Streaming supported (stream: true). No API key, no signup.

Input

Example output

{
  "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",
    "served": "openai/gpt-4o-mini"
  }
}

Try it — see the 402 challenge (free)

curl -i -X POST https://agent402.tools/v1/auto/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Reply with exactly: OK"}],"max_tokens":5}'

The response is HTTP 402 Payment Required with exact payment requirements. Any x402 v2 client pays automatically and retries:

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();
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/v1/auto/chat/completions", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "messages": [
      {
        "role": "user",
        "content": "Reply with exactly: OK"
      }
    ],
    "max_tokens": 5
  }),
});

Related tools