Hosted Quickstart wizard

// Example only: code you own. Calls sent direct are not routed, recorded, budget-checked or billed.
// Use the provider's own model name (gpt-4.1): Parezen accepts it, so the same request works direct.
import OpenAI from "openai";

const viaParezen = new OpenAI({
  baseURL: "https://api.parezen.com/v1",
  apiKey: process.env.PAREZEN_API_KEY,
  // The timeout covers the whole answer, so keep it longer than your slowest reply.
  // A short one would resend slow answers to the provider and pay for them twice.
  timeout: 120_000,
  maxRetries: 0,
});
const direct = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

// After 3 failures in a row, go direct for 60 seconds instead of waiting on Parezen each time.
let failures = 0;
let directUntil = 0;

function parezenDown(err) {
  // Connection, DNS, TLS and timeout errors, or a 5xx. Never a 4xx such as a budget hard stop.
  return err instanceof OpenAI.APIConnectionError || (err?.status ?? 0) >= 500;
}

export async function chat(params) {
  if (Date.now() < directUntil) return direct.chat.completions.create(params);
  try {
    const reply = await viaParezen.chat.completions.create(params);
    failures = 0;
    return reply;
  } catch (err) {
    if (!parezenDown(err)) throw err; // a 4xx, including a budget hard stop, must not be bypassed
    failures += 1;
    if (failures >= 3) directUntil = Date.now() + 60_000;
    return direct.chat.completions.create(params);
  }
}

# Example only: code you own. Calls sent direct are not routed, recorded, budget-checked or billed.
# Use the provider's own model name (gpt-4.1): Parezen accepts it, so the same request works direct.
import os
import time
import openai
from openai import OpenAI

via_parezen = OpenAI(
    base_url="https://api.parezen.com/v1",
    api_key=os.environ["PAREZEN_API_KEY"],
    # The timeout covers the whole answer, so keep it longer than your slowest reply.
    # A short one would resend slow answers to the provider and pay for them twice.
    timeout=120,
    max_retries=0,
)
direct = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

# After 3 failures in a row, go direct for 60 seconds instead of waiting on Parezen each time.
failures = 0
direct_until = 0.0

def parezen_down(err):
    # Connection, DNS, TLS and timeout errors, or a 5xx. Never a 4xx such as a budget hard stop.
    return isinstance(err, (openai.APIConnectionError, openai.InternalServerError))

def chat(**params):
    global failures, direct_until
    if time.monotonic() < direct_until:
        return direct.chat.completions.create(**params)
    try:
        reply = via_parezen.chat.completions.create(**params)
        failures = 0
        return reply
    except Exception as err:
        if not parezen_down(err):
            raise  # a 4xx, including a budget hard stop, must not be bypassed
        failures += 1
        if failures >= 3:
            direct_until = time.monotonic() + 60
        return direct.chat.completions.create(**params)