Chat Completions

Last 30 days

Uptime

100%

Response time

257 ms typical, 333 ms slowest 5%

Last check

8 min ago

Next check

in 19 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://onchainrouter.dev/v1/chat/completions" \
  -H "content-type: application/json" \
  -d '{"max_tokens":512,"messages":[{"content":"Hello","role":"user"}],"model":"gemini-3.6-flash","stream":false}'

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%2Fonchainrouter.dev%2Fv1%2Fchat%2Fcompletions
const res = await pay("https://onchainrouter.dev/v1/chat/completions", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"max_tokens":512,"messages":[{"content":"Hello","role":"user"}],"model":"gemini-3.6-flash","stream":false}),
});
console.log(await res.json());

Example input

{
  "max_tokens": 512,
  "messages": [
    {
      "content": "Hello",
      "role": "user"
    }
  ],
  "model": "gemini-3.6-flash",
  "stream": false
}

Example output

{
  "choices": [],
  "id": "chatcmpl_example",
  "model": "gemini-3.6-flash",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}

Security scan

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

Recent checks