Image generation with Virouter

Quick start

Node.js example

Use the OpenAI SDK's images.generate() method with Virouter baseURL.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.VIROUTER_API_KEY,
  baseURL: "https://api.virouter.com/v1",
});

const response = await client.images.generate({
  model: "gpt-image-2",
  prompt: "A cat sitting on a beach at sunset",
  n: 1,
  size: "1024x1024",
  quality: "low", // low, medium, or high
});

console.log(response.data[0].url);
// or save base64: response.data[0].b64_json

Python example

The Python SDK uses the same images.generate() interface.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["VIROUTER_API_KEY"],
    base_url="https://api.virouter.com/v1",
)

response = client.images.generate(
    model="gpt-image-2",
    prompt="A minimalist tech logo with circuit paths",
    n=1,
    size="1024x1024",
    quality="medium",
)

print(response.data[0].url)
# or decode base64: response.data[0].b64_json

cURL example

Direct HTTP POST for testing or server-side scripts.

curl https://api.virouter.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $VIROUTER_API_KEY" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A red circle on white background",
    "n": 1,
    "size": "1024x1024",
    "quality": "low"
  }'

Response format

By default, Virouter returns base64-encoded images in the b64_json field. Decode and save as PNG.

{
  "created": 1781055119,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAAA...",
      "revised_prompt": "A simple red circle centered on a plain white background..."
    }
  ],
  "model": "gpt-image-2",
  "usage": {
    "input_tokens": 24,
    "output_tokens": 196,
    "total_tokens": 220
  }
}

Quality vs speed

Set your HTTP client timeout to at least 150 seconds to avoid premature disconnects during image generation.

Troubleshooting