Chat completions - Ox Alpha (stealth preview, prompts shared)

OpenAI-compatible chat completions served by Ox Alpha (stealth/ox-alpha), a reasoning model with a 1,048,576-token context window. FREE TO USE while the model's own upstream is free: add ?trial=1 and no wallet, key or signup is needed (a per-client allowance, and the response says how much is left). $0.002 per call in USDC over x402 when you want it without an allowance. The model is locked to this route (sending a different model returns a 400 naming its tier). Reasoning is always on; the gateway sets effort "low" by default and you can raise it with reasoning.effort ("low", "high" or "max"). Text and image input, up to 80,000 chars per request (the HTTP body limit, not the model's context) and 8,000 output tokens. Streaming supported (stream: true). PROMPTS ARE SHARED WITH THE MODEL PROVIDER: this is a stealth (cloaked) preview listing, served at no upstream cost in exchange for the provider RETAINING and reviewing the prompts and completions sent through it. Do not send confidential or personal data on this route; zdr:true is refused here and works on every priced tier instead. The model can also be withdrawn by its provider at any time, at which point this route answers 503 (never a charge).

TRY IN PLAYGROUND →

Input

Example output

{
  "id": "gen-…",
  "object": "chat.completion",
  "created": 1750000000,
  "model": "stealth/ox-alpha",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 1,
    "total_tokens": 13
  }
}

Try it - see the 402 challenge (free)

curl -i -X POST https://agent402.tools/v1/ox/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Reply with exactly: OK"}],"max_tokens":1024}'

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/ox/chat/completions", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "messages": [
      {
        "role": "user",
        "content": "Reply with exactly: OK"
      }
    ],
    "max_tokens": 1024
  }),
});

Related tools