Model Picks

Last 30 days

Uptime

100%

Response time

202 ms typical, 548 ms slowest 5%

Last check

1 h ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X GET "https://mini-tollbooth.onrender.com/model-picks?task=coding"

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

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fmini-tollbooth.onrender.com%2Fmodel-picks
const res = await pay("https://mini-tollbooth.onrender.com/model-picks?task=coding");
console.log(await res.json());

Example input

{
  "task": "coding"
}

Example output

{
  "best_value": {
    "id": "deepseek/deepseek-chat"
  },
  "description": "Best model per dollar — curated quality scores per task (coding, writing, reasoning, chat) joined with live per-token pricing, ranked by value. Quality is a curated benchmark snapshot, not a live measurement.",
  "lane": "/model-picks",
  "quality_snapshot": "curated benchmark snapshot 2026-10-01",
  "task": "coding"
}

Security scan

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

Recent checks