ToolVet
77trust / 100

Chat Completions

by Agent Hub in AI models & inference

x402 APIPassing, checked 18 min ago

OpenAI-compatible chat completions on OpenAI gpt-oss-120b, the strongest open-weight OpenAI model, reasoning with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/gpt-oss and pay $0.006 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Also callable as GET with the same fields as query parameters.

GET https://agents.torbrooknews.com/v1/gpt-oss/chat/completions

Last 30 days

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

Uptime
100%
Response time
674 ms typical, 1.3 s slowest 5%
Last check
18 min ago
Next check
in 12 min

How to call it

GET https://agents.torbrooknews.com/v1/gpt-oss/chat/completions

Each call costs $0.006 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

GET https://agents.torbrooknews.com/v1/gpt-oss/chat/completions?prompt=Say+hello+in+French.

Parameters

ParameterTypeRequiredDescription
max_tokensintegerNo
promptstringYesUser message
systemstringNoOptional system message
temperaturenumberNo

Example response

The provider's example. We can't check it without paying.

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Bonjour !",
        "role": "assistant"
      }
    }
  ],
  "id": "chatcmpl-...",
  "model": "gpt-oss-120b",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 4,
    "prompt_tokens": 14,
    "total_tokens": 18
  }
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.006.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://agents.torbrooknews.com/v1/gpt-oss/chat/completions?prompt=Say+hello+in+French.'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - 'https://agents.torbrooknews.com/v1/gpt-oss/chat/completions?prompt=Say+hello+in+French.' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.006 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.006" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.006 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagents.torbrooknews.com%2Fv1%2Fgpt-oss%2Fchat%2Fcompletions
const res = await pay("https://agents.torbrooknews.com/v1/gpt-oss/chat/completions?prompt=Say+hello+in+French.");
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.006 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.006"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.get("https://agents.torbrooknews.com/v1/gpt-oss/chat/completions?prompt=Say+hello+in+French.")
    print(res.status_code, res.text)

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
18 min agoPassed4021.3 s$0.006
4 h agoPassed402726 ms$0.006
8 h agoPassed402148 ms$0.006
12 h agoPassed402129 ms$0.006
16 h agoPassed402112 ms$0.006
20 h agoPassed402697 ms$0.006
24 h agoPassed402674 ms$0.006
27 h agoPassed4024.9 s$0.006
36 h agoPassed40237 ms$0.006