GPT Image 2 API

Complete API reference for GPT Image 2 models powered by OpenAI.

Model Variants

This API supports four model variants:

Quick Comparison

Supported Aspect Ratios

16:9, 9:16, 1:1, 3:2, 2:3, 3:4, 4:3, 5:4, 4:5, 21:9

GPT Image 2 (Text-to-Image)

Endpoint

POST /api/v1/image/task

Authentication

Authorization: Bearer YOUR_API_KEY

Request Parameters

Required

Note: The width:height ratio must be one of: 16:9, 9:16, 1:1, 3:2, 2:3, 3:4, 4:3, 5:4, 4:5, 21:9

Example Request

javascriptCopy
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'gpt-image-2',
    prompt: 'A minimalist product shot of a ceramic mug on marble, soft studio light',
    width: 1,
    height: 1,
    resolution: '1k',
    quality: 'medium'
  })
});

const { data } = await response.json();
const taskId = data.task_id;

// Poll for results
const pollResponse = await fetch(
  `https://api.flaq.ai/api/v1/image/${taskId}`,
  {
    headers: { Authorization: 'Bearer YOUR_API_KEY' }
  }
);

const result = await pollResponse.json();
console.log(result.data.task_result.images[0].url);

GPT Image 2 Edit (Image Editing)

Endpoint

POST /api/v1/image/task

Request Parameters

Required

Optional

Note: When width and height are provided, the ratio must be one of: 16:9, 9:16, 1:1, 3:2, 2:3, 3:4, 4:3, 5:4, 4:5, 21:9

Single Image Edit Example

javascriptCopy
{
  model_name: 'gpt-image-2-edit',
  prompt: 'Replace the background with a clean studio scene and brighten the product lighting',
  image_url_list: ['https://example.com/product-photo.jpg'],
  width: 16,
  height: 9,
  resolution: '1k',
  quality: 'medium'
}

Multi-Image Composition Example

javascriptCopy
{
  model_name: 'gpt-image-2-edit',
  prompt: 'Blend these reference images into a polished campaign composition while keeping the main subject identity consistent',
  image_url_list: [
    'https://example.com/image1.jpg',
    'https://example.com/image2.jpg',
    'https://example.com/image3.jpg'
  ],
  width: 16,
  height: 9,
  resolution: '2k',
  quality: 'high'
}

GPT Image 2 Client

Uses the same parameters and capabilities as GPT Image 2, with model_name set to gpt-image-2-client. This is a preview experience variant and may be less stable.

Example Request

javascriptCopy
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'gpt-image-2-client',
    prompt: 'A luxury skincare still life with soft reflections and elegant typography',
    width: 4,
    height: 5,
    resolution: '1k',
    quality: 'medium'
  })
});

const { data } = await response.json();
const taskId = data.task_id;

GPT Image 2 Edit Client

Uses the same parameters and capabilities as GPT Image 2 Edit, with model_name set to gpt-image-2-edit-client. This is a preview experience variant and may be less stable.

Example Request

javascriptCopy
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'gpt-image-2-edit-client',
    prompt: 'Turn this portrait into a clean editorial poster while preserving the face and pose',
    image_url_list: ['https://example.com/portrait.jpg'],
    width: 4,
    height: 5,
    resolution: '1k',
    quality: 'medium'
  })
});

const { data } = await response.json();
const taskId = data.task_id;

Response Format

Initial Response

All GPT Image 2 variants return a task_id for polling:

jsonCopy
{
  "code": 0,
  "data": {
    "task_id": "{task_id}",
    "task_status": "submitted",
    "response_url": "https://api.flaq.ai/api/v1/image/{task_id}"
  },
  "message": "success"
}

Polling Response

Poll GET /api/v1/image/{task_id} to check status:

jsonCopy
{
  "code": 0,
  "data": {
    "task_id": "{task_id}",
    "task_status": "succeed",
    "task_status_msg": null,
    "response_url": "https://api.flaq.ai/api/v1/image/{task_id}",
    "task_result": {
      "credit": 0.0997,
      "images": [
        {
          "url": "https://example.com/generated-image.jpeg"
        }
      ]
    }
  },
  "message": "success"
}

Status Values

• submitted: Task accepted
• processing: Image generation or editing in progress
• succeed: Task completed successfully
• failed: Task failed

Processing Time

Typical processing time is 15-60 seconds depending on resolution, quality, prompt complexity, and image count for edit requests.

Best Practices

1. Be explicit about composition: GPT Image 2 performs best when prompts describe subject, framing, lighting, and intended style clearly.
2. Choose quality based on workflow: Use low or medium for iteration, and high for polished output.
3. Match aspect ratio to delivery target: Set the ratio up front for social posts, banners, product pages, or editorial layouts.
4. Use clean source images for edits: Sharp, well-lit inputs improve identity preservation and local edit quality.
5. Limit multi-image requests to strong references: For edit variants, provide only the images that matter to avoid conflicting visual guidance.