Examples

Working snippets in four languages. Replace YOUR_API_TOKEN with the token from Getting started.

Each snippet below sends the same prompt to POST /api/ai and prints the assistant text. They are intentionally minimal: no SDK, no clever wrappers, just the standard library or a single well-known HTTP client per language.

curl

Shell

curl https://scouq.com/api/ai \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b-versatile",
    "messages": [
      { "role": "user", "content": "ARV 240000, rehab 28000, asking 145000. Quick take on the 70 percent rule?" }
    ],
    "max_tokens": 250,
    "temperature": 0.3
  }' | jq -r '.choices[0].message.content'

Python

Standard library only. Works on Python 3.8+.

Python

import json
import os
import urllib.request

TOKEN = os.environ["SCOUQ_API_TOKEN"]

body = {
    "model": "llama-3.3-70b-versatile",
    "messages": [
        {"role": "user", "content": "ARV 240000, rehab 28000, asking 145000. Quick take on the 70 percent rule?"}
    ],
    "max_tokens": 250,
    "temperature": 0.3,
}

req = urllib.request.Request(
    "https://scouq.com/api/ai",
    data=json.dumps(body).encode("utf-8"),
    headers={
        "Authorization": "Bearer " + TOKEN,
        "Content-Type": "application/json",
    },
    method="POST",
)

with urllib.request.urlopen(req, timeout=30) as resp:
    data = json.loads(resp.read())

print(data["choices"][0]["message"]["content"])

With requests:

Python (requests)

import os
import requests

r = requests.post(
    "https://scouq.com/api/ai",
    headers={"Authorization": "Bearer " + os.environ["SCOUQ_API_TOKEN"]},
    json={
        "model": "llama-3.3-70b-versatile",
        "messages": [
            {"role": "user", "content": "ARV 240000, rehab 28000, asking 145000. Quick take?"}
        ],
        "max_tokens": 250,
        "temperature": 0.3,
    },
    timeout=30,
)
r.raise_for_status()
print(r.json()["choices"][0]["message"]["content"])

Rust

Uses reqwest with the blocking feature and serde_json. Add to Cargo.toml:

Cargo.toml

[dependencies]
reqwest = { version = "0.12", features = ["blocking", "json"] }
serde_json = "1"

Rust

use serde_json::{json, Value};
use std::env;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let token = env::var("SCOUQ_API_TOKEN")?;

    let body = json!({
        "model": "llama-3.3-70b-versatile",
        "messages": [
            { "role": "user", "content": "ARV 240000, rehab 28000, asking 145000. Quick take?" }
        ],
        "max_tokens": 250,
        "temperature": 0.3
    });

    let client = reqwest::blocking::Client::new();
    let resp: Value = client
        .post("https://scouq.com/api/ai")
        .bearer_auth(token)
        .json(&body)
        .send()?
        .error_for_status()?
        .json()?;

    let text = resp["choices"][0]["message"]["content"]
        .as_str()
        .unwrap_or("");
    println!("{}", text);
    Ok(())
}

Node

Node 18+ has fetch built in. No dependencies needed.

Node (JavaScript)

const token = process.env.SCOUQ_API_TOKEN;

async function main() {
  const resp = await fetch("https://scouq.com/api/ai", {
    method: "POST",
    headers: {
      "Authorization": "Bearer " + token,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      model: "llama-3.3-70b-versatile",
      messages: [
        { role: "user", content: "ARV 240000, rehab 28000, asking 145000. Quick take?" }
      ],
      max_tokens: 250,
      temperature: 0.3
    })
  });

  if (!resp.ok) {
    const err = await resp.text();
    throw new Error("HTTP " + resp.status + ": " + err);
  }

  const data = await resp.json();
  console.log(data.choices[0].message.content);
}

main().catch(function (e) { console.error(e); process.exit(1); });

Handling rate limits

Add a one-shot retry on 429 with Retry-After. This pattern works in every language; the Python version below is representative.

Python

import time
import requests

def call_with_retry(token, body, max_retries=2):
    url = "https://scouq.com/api/ai"
    headers = {"Authorization": "Bearer " + token}
    for attempt in range(max_retries + 1):
        r = requests.post(url, headers=headers, json=body, timeout=30)
        if r.status_code != 429:
            r.raise_for_status()
            return r.json()
        wait = int(r.headers.get("Retry-After", "30"))
        time.sleep(wait)
    r.raise_for_status()