OpenAI SDK through Model Gate

Python

from openai import OpenAI

client = OpenAI(
    api_key="mg_live_...",
    base_url="https://api.model-gate.com/v1",
)

response = client.chat.completions.create(
    model="ch-47",
    messages=[{"role": "user", "content": "Hello"}],
)

print(response.choices[0].message.content)

Responses API

response = client.responses.create(
    model="gpt-5.4",
    input="Summarize this release.",
)
print(response.output_text)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MODEL_GATE_API_KEY,
  baseURL: "https://api.model-gate.com/v1",
});

const response = await client.chat.completions.create({
  model: "ch-46s",
  messages: [{ role: "user", content: "Hello" }],
});

console.log(response.choices[0].message.content);

Dedicated Images integration

The examples above are text calls. An Images integration must explicitly send a stable Idempotency-Key, use the reviewed model/route settings and handle both a completed result and HTTP 202 with an operation ID. Do not assume a high-level SDK image method understands Model Gate polling, private file URLs or the model_gate extension. Disable automatic paid POST retries in the client; read the existing operation after a timeout. The generation, edit and operation HTTP contracts are authoritative.