OpenAI image generation and editing examples

Endpoints

GPT Image 2 parameters

Parameter	Endpoint	Values and behavior
`model`	Generations, edits	Set `gpt-image-2` to use GPT Image 2; when omitted, ApiGo defaults to `dall-e-2`
`size`	Generations, edits	Common values include `1024x1024`, `1536x1024`, `1024x1536`, `2048x2048`, `2048x1152`, and `auto`; custom resolutions are also accepted when they satisfy the size constraints
`quality`	Generations, edits	`low`, `medium`, `high`, or `auto`; ApiGo uses `medium` when the field is omitted
`n`	Generations, edits	Number of returned images; ApiGo uses `1` when omitted
`background`	Generations, edits	`opaque` or `auto`; `gpt-image-2` does not support `transparent`
`output_format`	Generations, edits	`png`, `jpeg`, or `webp`; defaults to `png`
`output_compression`	Generations, edits	JPEG/WebP compression from 0–100
`moderation`	Generations, edits	`auto` or `low`
`input_fidelity`	Edits	`gpt-image-2` always processes input images at high fidelity, so omit this parameter

Generate an image

cURL

curl https://api-vip.apigo.ai/v1/images/generations \
  -H "Authorization: Bearer $APIGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A clean ApiGo product poster with a deep blue background, crisp title, and modern technology style",
    "size": "1024x1024",
    "quality": "medium",
    "output_format": "png"
  }'

Python

import base64
import os
from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://api-vip.apigo.ai/v1",
    api_key=os.environ["APIGO_API_KEY"],
)

result = client.images.generate(
    model="gpt-image-2",
    prompt="A clean ApiGo product poster with a deep blue background, crisp title, and modern technology style",
    size="1024x1024",
    quality="medium",
    output_format="png",
)

Path("apigo-poster.png").write_bytes(
    base64.b64decode(result.data[0].b64_json)
)

Node.js

import OpenAI from "openai";
import { writeFile } from "node:fs/promises";

const client = new OpenAI({
  baseURL: "https://api-vip.apigo.ai/v1",
  apiKey: process.env.APIGO_API_KEY,
});

const result = await client.images.generate({
  model: "gpt-image-2",
  prompt: "A clean ApiGo product poster with a deep blue background, crisp title, and modern technology style",
  size: "1024x1024",
  quality: "medium",
  output_format: "png",
});

await writeFile(
  "apigo-poster.png",
  Buffer.from(result.data[0].b64_json, "base64"),
);

Edit an image

cURL

curl https://api-vip.apigo.ai/v1/images/edits \
  -H "Authorization: Bearer $APIGO_API_KEY" \
  -F 'model=gpt-image-2' \
  -F 'prompt=Replace the orange cat with a panda while preserving the composition and lighting' \
  -F 'size=1536x1024' \
  -F 'quality=medium' \
  -F 'image=@source.png'

For multiple input images, repeat image[]:

-F 'image[]=@source.png' \
-F 'image[]=@reference.png'

Python

import base64
import os
from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://api-vip.apigo.ai/v1",
    api_key=os.environ["APIGO_API_KEY"],
)

with open("source.png", "rb") as source:
    result = client.images.edit(
        model="gpt-image-2",
        image=source,
        prompt="Replace the orange cat with a panda while preserving the composition and lighting",
        size="1536x1024",
        quality="medium",
    )

Path("edited.png").write_bytes(
    base64.b64decode(result.data[0].b64_json)
)

Node.js

import fs from "node:fs";
import { writeFile } from "node:fs/promises";
import OpenAI, { toFile } from "openai";

const client = new OpenAI({
  baseURL: "https://api-vip.apigo.ai/v1",
  apiKey: process.env.APIGO_API_KEY,
});

const result = await client.images.edit({
  model: "gpt-image-2",
  image: await toFile(fs.createReadStream("source.png"), "source.png", {
    type: "image/png",
  }),
  prompt: "Replace the orange cat with a panda while preserving the composition and lighting",
  size: "1536x1024",
  quality: "medium",
});

await writeFile(
  "edited.png",
  Buffer.from(result.data[0].b64_json, "base64"),
);

Mask

The mask must use the same format and dimensions as the first input image and contain an alpha channel. Transparent areas identify the region to edit; GPT Image treats the mask as guidance, so the result may not follow its boundary exactly. With multiple inputs, the mask applies only to the first image.

-F 'mask=@mask.png'

Response

Both endpoints return Base64-encoded image data and token usage. For edit requests, input_tokens_details.image_tokens includes input-image usage:

{
  "created": 1784268912,
  "data": [
    {
      "b64_json": "iVBORw0KGgoAAA..."
    }
  ],
  "usage": {
    "input_tokens": 1549,
    "input_tokens_details": {
      "image_tokens": 1536,
      "text_tokens": 13
    },
    "output_tokens": 1372,
    "output_tokens_details": {
      "image_tokens": 1372,
      "text_tokens": 0
    },
    "total_tokens": 2921
  }
}

usage reports token counts, not the final billed amount. Actual charges follow the model prices, discounts, and billing records shown by ApiGo.

Interface Guide

API Endpoints

Usage Examples

OpenAI image generation and editing examples

Endpoints

GPT Image 2 parameters

Generate an image

cURL

Python

Node.js

Edit an image

cURL

Python

Node.js

Mask

Response

​Endpoints

​GPT Image 2 parameters

​Generate an image

​cURL

​Python

​Node.js

​Edit an image

​cURL

​Python

​Node.js

​Mask

​Response

Endpoints

GPT Image 2 parameters

Generate an image

cURL

Python

Node.js

Edit an image

cURL

Python

Node.js

Mask

Response