---
title: GPT Image 2 | Runware Docs
url: https://runware.ai/docs/models/openai-gpt-image-2
description: Image generation and editing model with strong prompt fidelity, text rendering, and layout-aware control
---
# GPT Image 2

![GPT Image 2](https://assets.runware.ai/covers/openai-gpt-image-2.jpg)

GPT Image 2 is a general-purpose GPT Image family model for text-to-image generation and image editing. Its strengths include strong prompt adherence, readable embedded text, detailed edits, photorealistic rendering, and structured visual outputs such as posters, packaging, product comps, diagrams, and other layout-sensitive images.

- **Status**: deprecated
- **ID**: `openai:gpt-image@2`
- Try in Playground
- **Creator**: OpenAI
- **Release Date**: April 21, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint, Transparency

## Pricing

~$0.0324 typical run

**Rates** (per 1M tokens)

- Text input: `$5.00`
- Image input: `$8.00`
- Image output: `$30.00`

**4 example generations**

- [transparent-background](https://runware.ai/docs/models/openai-gpt-image-2/examples#example-rail-signal-training-character-portrait): `$0.0221` (~35s)
- [inpaint](https://runware.ai/docs/models/openai-gpt-image-2/examples#example-municipal-water-tower-lighting-visualization): `$0.0223` (~23s)
- [text-to-image](https://runware.ai/docs/models/openai-gpt-image-2/examples#example-wadden-sea-walking-campaign-hero): `$0.0426` (~44s)
- [reference-to-image](https://runware.ai/docs/models/openai-gpt-image-2/examples#example-blackstart-grid-strategy-key-art): `$0.0675` (~43s)

billed per token, so a request costs what the model produced · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `inputs.maskImage` is provided, `inputs.referenceImages` is required.

---

`width` and `height` must be used together.

## Notes

**Supported dimensions:** Width and height must produce a total pixel area between **655,360** and **8,294,400**, with a maximum aspect ratio of **3:1**.

**Recommended dimensions:**

| Aspect Ratio | Width × Height |
| --- | --- |
| 1:1 | 1024 × 1024 |
| 3:2 | 1536 × 1024 |
| 2:3 | 1024 × 1536 |
| 16:9 | 2560 × 1440 |
| 16:9 (4K) | 3840 × 2160 |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/openai-gpt-image-2#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/openai-gpt-image-2#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/openai-gpt-image-2#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/openai-gpt-image-2#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/openai-gpt-image-2#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/openai-gpt-image-2#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/openai-gpt-image-2#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/openai-gpt-image-2#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/openai-gpt-image-2#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/openai-gpt-image-2#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

### [ttl](https://runware.ai/docs/models/openai-gpt-image-2#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/openai-gpt-image-2#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/openai-gpt-image-2#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [maskImage](https://runware.ai/docs/models/openai-gpt-image-2#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`

Image used to specify which areas of the input image should be edited (UUID, URL, Data URI, or Base64). Must have the same width and height as the first reference image. White marks the area to edit, black is preserved. The model treats the mask as guidance rather than a hard boundary, so edits can extend past its shape. With several reference images the mask applies to the first.

### [referenceImages](https://runware.ai/docs/models/openai-gpt-image-2#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `16`

List of reference images (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/openai-gpt-image-2#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `openai:gpt-image@2`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/openai-gpt-image-2#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `32000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/openai-gpt-image-2#request-width)

- **Type**: `integer`
- **Min**: `16`
- **Max**: `3840`
- **Step**: `16`

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/openai-gpt-image-2#request-height)

- **Type**: `integer`
- **Min**: `16`
- **Max**: `3840`
- **Step**: `16`

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [background](https://runware.ai/docs/models/openai-gpt-image-2#request-settings-background)

- **Path**: `settings.background`
- **Type**: `string`
- **Default**: `auto`

Background handling in generated images.

**Allowed values**: `auto` `opaque`

### [moderation](https://runware.ai/docs/models/openai-gpt-image-2#request-settings-moderation)

- **Path**: `settings.moderation`
- **Type**: `string`
- **Default**: `auto`

Content moderation level.

**Allowed values**:

- `auto` Standard filtering that limits creating certain categories of potentially age-inappropriate content.
- `low` Less restrictive filtering.

### [quality](https://runware.ai/docs/models/openai-gpt-image-2#request-settings-quality)

- **Path**: `settings.quality`
- **Type**: `string`
- **Default**: `auto`

Image quality level.

**Allowed values**: `auto` `high` `medium` `low`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/openai-gpt-image-2#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/openai-gpt-image-2#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/openai-gpt-image-2#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/openai-gpt-image-2#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/openai-gpt-image-2#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/openai-gpt-image-2#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/openai-gpt-image-2#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/openai-gpt-image-2#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/openai-gpt-image-2#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-image (text-to-image)

![Wadden Sea Walking Campaign Hero](https://assets.runware.ai/examples/openai-gpt-image-2/bacf3cd9-4b0d-474a-869e-9258c22d0b74.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "c2b7425b-ad4c-46d0-9625-6adbc4f8d1de",
  "model": "openai:gpt-image@2",
  "positivePrompt": "Create a premium landscape tourism campaign photograph promoting guided wadlopen, or mudflat hiking, in the Dutch Wadden Sea. At low tide, a small group of six adult travelers follows an experienced local guide across vast rippled tidal flats toward a distant Frisian island. Show them mid-stride in practical outdoor clothing and knee-high boots, carrying compact daypacks; the guide leads with a tall red safety pennant. Shallow channels mirror the sky around their boots, with tiny shells, wet sand textures, and scattered seabirds visible in the foreground. Far behind them, include a low green dike, a small white lighthouse, and two traditional flat-bottomed sailboats resting on the exposed sand. A dramatic North Sea rain squall clears from left to right, opening onto warm late-afternoon sunlight that illuminates the hikers and turns the reflective flats silver and pale gold. Wide, low viewpoint emphasizing the immense horizon, layered clouds, human scale, and exhilarating sense of reaching a remote island on foot. High-end editorial travel photography, natural skin tones, crisp environmental detail, subtle film grain, restrained palette of slate blue, sea green, sand, cream, and one vivid red accent. Authentic, windswept, adventurous, calm rather than extreme. Compose as a polished standalone tourism hero image with visual interest across the full landscape frame. No text, logos, borders, collage, illustration, or interface elements.",
  "width": 1536,
  "height": 1024
}
```

---

### reference-to-image (reference-to-image)

![Blackstart Grid Strategy Key Art](https://assets.runware.ai/examples/openai-gpt-image-2/1802a1eb-72b4-4d53-8bff-8fd1b07349e4.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "b1dd713b-35b5-430a-a70c-56e8a14d5508",
  "model": "openai:gpt-image@2",
  "positivePrompt": "Create finished vertical 2:3 key art for a premium narrative strategy game titled “BLACKSTART.” Meaningfully combine both reference images: preserve the recognizable face, cropped hair, orange-and-charcoal insulated workwear, harness and practical equipment of the technician from reference image 1, and preserve the distinctive stepped spillway towers, monumental concrete geometry, switchyard and steep snowy valley from reference image 2. Show the technician in a heroic but grounded three-quarter back view on an icy maintenance gantry, turning her face toward the viewer while looking over the powerless dam complex. She holds a rugged field terminal displaying only abstract grid lines, with no readable interface text. Below her, one section of the switchyard has just re-energized: a chain of warm amber maintenance lights cuts through the deep cobalt blackout while distant transmission pylons disappear into blowing snow. Convey infrastructure expertise, isolation, urgency and cautious hope rather than combat.\n\nArt direction: sophisticated hand-painted game key art combining realist environmental concept painting with bold mid-century industrial poster shapes; crisp architectural silhouettes, restrained brush texture, cinematic atmospheric depth, subtle screenprint grain. Palette dominated by midnight cobalt, storm gray and snow white, with safety orange on the character and a narrow amber electrical glow. Strong triangular composition leading from the foreground technician to the dam and then the mountain pass. Dramatic rim light, wind-driven snow, visible scale, believable engineering details. Reserve the upper fifth as dark storm sky and place the exact title BLACKSTART there in large condensed uppercase off-white lettering, clean and highly legible, with generous tracking. No subtitle, logos, badges, credits or other words. Standalone game cover artwork, edge-to-edge image, not a box mockup, screenshot or user interface.",
  "width": 1024,
  "height": 1536,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/6d46cb0b-3aed-45f6-982d-4ddd3b2576b2.jpg",
      "https://assets.runware.ai/assets/inputs/85639017-4246-4761-99ab-6ed09e02b254.jpg"
    ]
  }
}
```

---

### inpaint (inpaint)

![Municipal Water Tower Lighting Visualization](https://assets.runware.ai/examples/openai-gpt-image-2/3887c57e-64ab-48c0-a7cd-e7df9bc6e979.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e5c7da02-5a6a-4b07-a11d-815a4828a4d2",
  "model": "openai:gpt-image@2",
  "positivePrompt": "Create a finished photorealistic architectural lighting visualization using the reference photograph as the base. The mask covers the complete water tower: remove the original unlit tower and replace it with the same tower reconstructed at exactly the same scale, position, geometry, camera perspective, and silhouette. Relight the replacement tower as a refined municipal nighttime landmark: warm amber grazing light rising from discreet ground fixtures across the concrete support legs, a restrained soft golden glow beneath the tank, and a narrow cool-white rim light defining the circular crown. Keep the lighting plausible, elegant, and compliant with dark-sky design, with realistic falloff, subtle concrete texture, and no clipped highlights. Preserve the surrounding cobalt sky, gravel foreground, horizon, framing, and all unmasked areas exactly as photographed. Do not add people, vehicles, landscaping, fixtures in view, signage, logos, lettering, or extra structures.",
  "width": 1024,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/4ced95cc-465a-4bf8-a2a8-2a2bba411c7f.jpg"
    ],
    "maskImage": "https://assets.runware.ai/assets/inputs/eb692d7e-45fe-4e0f-b306-22d821cf7d06.png"
  }
}
```

---

### transparent-background (transparent-background)

![Rail Signal Training Character Portrait](https://assets.runware.ai/examples/openai-gpt-image-2/a07ba32e-de45-4060-87e8-7c35cd9057e2.png)

```json
{
  "taskType": "imageInference",
  "taskUUID": "64d68e06-7434-432a-ad80-fdd7e2a83cf3",
  "outputFormat": "PNG",
  "model": "openai:gpt-image@2",
  "positivePrompt": "Create a polished full-body character portrait of Mara Singh, a fictional veteran railway signal technician and recurring vocational-training persona. She is a sturdy 52-year-old South Asian woman with a heart-shaped face, warm brown skin, dark brown eyes, a small notch in her left eyebrow, and a chin-length black bob with a prominent silver streak over her right temple. She wears round amber safety glasses, deep aubergine work coveralls, a fitted chartreuse high-visibility vest with silver reflective bands, black steel-toe boots, and a compact orange signal-circuit tester clipped at her hip. No logos, lettering, badges, or brand marks. Confident but approachable expression, relaxed three-quarter stance, one hand resting near her tool belt and the other holding a pair of insulated work gloves. Premium stylized 3D editorial character design with tactile woven fabrics, subtly simplified proportions, realistic facial detail, restrained clay-like modeling, and soft studio-quality illumination. Preserve these distinctive identity and wardrobe details as a clear repeatable character specification. One subject only, completely isolated on a genuinely transparent background, clean production-ready silhouette, crisp edges around hair and clothing, no environment, no backdrop, no floor, no platform, no shadow, no props beyond her wearable tools and gloves. Landscape composition with the full figure centered slightly left, occupying about 82 percent of the canvas height, with generous transparent breathing room on the right for flexible training-layout use.",
  "width": 1280,
  "height": 1024,
  "settings": {
    "background": "transparent"
  }
}
```