---
title: GPT-Image-2.6 Flare | Runware Docs
url: https://runware.ai/docs/models/openai-gpt-image-2-6-flare
description: Fast image generation and editing for interactive iteration
---
# GPT-Image-2.6 Flare

![GPT-Image-2.6 Flare](https://assets.runware.ai/covers/openai-gpt-image-2-6-flare.jpg)

GPT-Image-2.6 Flare is OpenAI's fast image model for generation and editing in interactive workflows. Besides raster images, it generates SVG graphics and animated GIFs from text, and it edits images from marks drawn over them, like a circle around the object to change. A thinking level sets how much it plans before rendering, separate from rendering quality.

- **Status**: live
- **ID**: `openai:gpt-image@2.6-flare`
- Try in Playground
- **Creator**: OpenAI
- **Release Date**: November 5, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Vectorize, Checkpoint, Transparency

## Pricing

~$0.17 typical run

**Rates** (per 1M tokens)

- Text input: `$5.00`
- Image input: `$8.00`
- Image output: `$30.00`
- SVG authoring · GPT-5.4 Mini · Input: `$0.75`
- SVG authoring · GPT-5.4 Mini · Output: `$4.50`
- SVG authoring · GPT-5.4 · Input: `$2.50`
- SVG authoring · GPT-5.4 · Output: `$15.00`
- SVG authoring · GPT-5.5 · Input: `$5.00`
- SVG authoring · GPT-5.5 · Output: `$30.00`
- SVG authoring · GPT-5.6 Terra · Input: `$2.00`
- SVG authoring · GPT-5.6 Terra · Output: `$12.00`
- SVG authoring · GPT-6 Luna · Input: `$0.10`
- SVG authoring · GPT-6 Luna · Output: `$0.50`
- SVG authoring · GPT-6 Astra · Input: `$10.00`
- SVG authoring · GPT-6 Astra · Output: `$50.00`

**6 example generations**

- [inpaint](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/examples#example-mycology-benefit-supper-invitation): `$0.0587` (~14s)
- [text-to-gif](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/examples#example-analog-seismograph-blog-hero): `$0.118` (~12s)
- [text-to-image](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/examples#example-luthier-workshop-team-composite): `$0.167` (~30s)
- [text-to-vector](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/examples#example-urban-cooling-campaign-key-visual): `$0.174` (~37s)
- [transparent-background](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/examples#example-subsea-cable-robot-blog-hero): `$0.175` (~14s)
- [reference-to-image](https://runware.ai/docs/models/openai-gpt-image-2-6-flare/examples#example-electric-ferry-launch-invitation): `$0.193` (~19s)

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

Inside `inputs`, `maskImage` cannot be used with `markupImage`.

---

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

---

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

---

When `outputFormat` is `SVG, or GIF`, `inputs.referenceImages` cannot be used.

---

When `outputFormat` is `GIF`, `width` must be at most `960` and `height` must be at most `960`.

---

When `settings.background` is `transparent`, `outputFormat` is limited to `PNG`, `WEBP`.

---

When `settings.gif` is provided, `outputFormat` must be `GIF`.

---

When `settings.svg` is provided, `outputFormat` must be `SVG`.

---

When `settings.svg.model` is `openai:gpt@5.4-mini, openai:gpt@5.4, or openai:gpt@5.5`, `settings.svg.thinkingLevel` is limited to `none`, `low`, `medium`, `high`, `xhigh`.

---

When `settings.svg.model` is `openai:gpt@5.6-terra, or openai:gpt@6-luna`, `settings.svg.thinkingLevel` is limited to `none`, `low`, `medium`, `high`, `xhigh`, `max`.

---

When `settings.svg.model` is `openai:gpt@6-astra`, `settings.svg.thinkingLevel` is limited to `low`, `medium`, `high`, `xhigh`, `max`.

---

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

## Notes

GPT-Image-2.6 Flare picks its mode from the inputs you attach and the output format you ask for:

- **Text-to-image:** Provide a prompt on its own.
- **Editing:** Provide `inputs.referenceImages`. The first image is the one being edited, and any others bring in what it does not have.
- **Targeted editing:** Add `inputs.maskImage` or `inputs.markupImage` to an edit. Both point at part of the first reference image.
- **Vector and animation:** Set `outputFormat` to `SVG` or `GIF`, from a prompt alone.

**Two thinking levels:** `settings.thinkingLevel` sets how much the image model plans the composition, separately from the rendering effort in `settings.quality`. An SVG request carries a second, independent level in `settings.svg.thinkingLevel`, the reasoning of the language model that writes the SVG, and the values it accepts depend on `settings.svg.model`.

**SVG output:** the image model first renders a reference image, which `settings.quality` and `settings.thinkingLevel` shape, and the author model writes the SVG from it. The author's tokens are billed at that model's own rate on top of the image tokens. Without `width` and `height`, the model picks the canvas.

**GIF output:** every frame is drawn on one sheet and cut out of it, which is why the largest frame size shrinks as `settings.gif.frameCount` grows. Without `settings.gif`, a GIF has 9 frames shown for 0.2 seconds each, and without `width` and `height` the frames are 512 × 512. The file loops forever.

**Markup:** `inputs.markupImage` is a transparent PNG with marks drawn over the first reference image, such as a circle around the object to change. The prompt refers to the mark, as in "the lamp inside the red circle", and asks for it to be removed from the result.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#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-2-6-flare#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-outputformat)

- **Type**: `string`
- **Required**: conditional — Required when settings.background is provided or settings.gif is provided or settings.svg is provided
- **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.
- \`GIF\`: Animated image format (no audio), suitable for short loops or previews.
- \`SVG\`: Scalable Vector Graphics.

> [!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` `SVG` `GIF`

### [outputQuality](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time.

### [ttl](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`
- **Formats**: `png`
- **File size**: `up to 50 MB`

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-2-6-flare#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `16`
- **File size (each)**: `up to 50 MB`

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

### [markupImage](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-inputs-markupimage)

- **Path**: `inputs.markupImage`
- **Type**: `string`
- **Formats**: `png`
- **Area**: `up to 16.78 MP`
- **File size**: `up to 50 MB`

Image with marks drawn over the first reference image to show where to edit (UUID, URL, Data URI, or Base64). Must have the same width and height as the first reference image and contain transparent pixels. With a markup image, the first reference image can have at most 16,777,216 pixels.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `openai:gpt-image@2.6-flare`

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-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#request-settings-background)

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

Background handling in generated images.

**Allowed values**:

- `auto` Automatically determines the most appropriate background based on content.
- `opaque` Solid background, no transparency.
- `transparent` Transparent background areas where applicable.

### [gif](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-gif)

- **Path**: `settings.gif`
- **Type**: `object (2 properties)`

Animated GIF output options.

#### [frameCount](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-gif-framecount)

- **Path**: `settings.gif.frameCount`
- **Type**: `integer`
- **Min**: `2`
- **Max**: `16`

Number of frames in the animated GIF.

#### [frameDuration](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-gif-frameduration)

- **Path**: `settings.gif.frameDuration`
- **Type**: `float`
- **Min**: `0.02`
- **Max**: `655.35`
- **Step**: `0.01`

Display time of each GIF frame, in seconds.

### [moderation](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#request-settings-quality)

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

Image quality level.

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

### [svg](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-svg)

- **Path**: `settings.svg`
- **Type**: `object (2 properties)`

SVG output options.

#### [model](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-svg-model)

- **Path**: `settings.svg.model`
- **Type**: `string`
- **Default**: `openai:gpt@5.4-mini`

Language model that writes the SVG.

**Allowed values**: `openai:gpt@5.4-mini` `openai:gpt@5.4` `openai:gpt@5.5` `openai:gpt@5.6-terra` `openai:gpt@6-luna` `openai:gpt@6-astra`

#### [thinkingLevel](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-svg-thinkinglevel)

- **Path**: `settings.svg.thinkingLevel`
- **Type**: `string`

Controls the depth of internal reasoning the model performs before generating a response.

**Allowed values**: `none` `low` `medium` `high` `xhigh` `max`

### [thinkingLevel](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#request-settings-thinkinglevel)

- **Path**: `settings.thinkingLevel`
- **Type**: `string`
- **Default**: `high`

Controls the depth of internal reasoning the model performs before generating a response.

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

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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-2-6-flare#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-2-6-flare#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-2-6-flare#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/openai-gpt-image-2-6-flare#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)

![Luthier Workshop Team Composite](https://assets.runware.ai/examples/openai-gpt-image-2-6-flare/cb4c9f5a-fb46-460e-a049-0334839edccf.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e27400df-f726-4efe-aba8-067757509e78",
  "model": "openai:gpt-image@2.6-flare",
  "positivePrompt": "Create a finished, photorealistic editorial group portrait for the 40th-anniversary catalog of an independent violin-making workshop. The image should read as a seamless professional composite in which the workshop’s absent master luthier, an elegant Japanese woman in her late 60s, has been added naturally at the center of the existing group. Show seven craftspeople total, arranged in two relaxed rows around a heavy, scarred maple workbench. The master luthier stands centrally behind the bench, wearing a charcoal linen apron over a muted burgundy blouse, silver hair in a neat low bun, one hand resting naturally beside a half-finished violin. Match her scale, perspective, sharpness, warm window light, subtle skin reflections, contact shadows, and film grain perfectly to the surrounding team; she must feel physically present rather than pasted in. The other six makers vary in age, gender, and appearance, wearing practical earth-toned workshop clothing and aprons, with natural expressions and believable interpersonal spacing. Everyone looks toward the camera with quiet pride rather than exaggerated smiles.\n\nSet the portrait inside a visually rich old-world luthier atelier: honey-colored timber walls, tall multipane windows, hanging hand tools, curling wood shavings, clamps, varnish jars, calipers, gouges, violin molds, spruce and maple billets, and several unfinished violins suspended in the background. Keep every tool and instrument plausible and finely detailed without clutter obscuring faces. Use warm late-afternoon daylight from camera left, soft amber practical lamps deeper in the room, gentle chiaroscuro, restrained highlights on varnished wood, and realistic soft shadows beneath hands and bodies. Landscape composition at eye level, medium-wide 35mm documentary photography, all seven people fully visible from approximately mid-thigh upward, balanced ensemble spacing, central subject clearly integrated but not spotlighted. Premium cultural-magazine art direction, subdued amber, walnut, charcoal, oxblood, and cream palette, fine natural skin texture, subtle analog color negative character, crisp facial detail, coherent hands, no duplicate people, no warped instruments, no captions, no logos, no borders, no visible signs of compositing.",
  "width": 1536,
  "height": 1024
}
```

---

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

![Electric Ferry Launch Invitation](https://assets.runware.ai/examples/openai-gpt-image-2-6-flare/7d3eb0d7-fc3f-4211-b962-e813e0364f43.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "450f271a-d417-427f-ab3f-b0a8362e4b7b",
  "model": "openai:gpt-image@2.6-flare",
  "positivePrompt": "Create a finished 1024x1024 square digital event invitation for the ceremonial launch of a municipal electric ferry. Use reference image 1 as the primary subject reference: accurately retain the ferry’s recognizable low hull, window rhythm, upper deck and wheelhouse, but reinterpret it as a confident graphic illustration rather than reproducing the original photograph or background. Use reference image 2 as the visual design reference: adopt its bold mid-century maritime screen-print language, simplified geometric waves, navigation motifs, tactile ink grain, slight color misregistration and limited cobalt blue, safety orange, seafoam green and warm cream palette.\n\nCompose the invitation as a polished standalone flat artwork, not a photographed card, mockup, website, app screen or framed presentation. Place a large orange sun in the upper-right quadrant and the illustrated ferry sailing from left to right across the lower third, with rhythmic cobalt and seafoam wave bands creating forward motion. Integrate a few abstract signal-flag shapes as decorative accents without making them resemble letters. Reserve generous clean cream space for highly legible typography. Use a strong condensed geometric sans serif for the headline, paired with a clean modern sans serif for event details. Maintain clear hierarchy, balanced spacing and professional print-design precision.\n\nRender this exact text, spelled and punctuated exactly as written, with no additional words:\n\nHARBOR CURRENT\nYOU’RE INVITED\nELECTRIC FERRY LAUNCH\n\nFRIDAY 18 SEPTEMBER 2026\n6:30 PM\nPIER 6 • EAST BASIN\n\nFIRST SAILING • DECK SUPPER • LIVE BRASS\nBOARDING FROM 6:15 PM\nRSVP BY 4 SEPTEMBER\n\nMake HARBOR CURRENT the dominant headline near the top left, YOU’RE INVITED small above or beside it, and ELECTRIC FERRY LAUNCH clearly subordinate. Set the date, time and location as a compact, easy-to-scan information block in the center-left area. Place the final two detail lines neatly near the bottom without colliding with the ferry or waves. Ensure every character is sharp and readable at invitation size. The overall mood should feel civic, optimistic, contemporary and celebratory, with the charm of a collectible harbor poster.",
  "width": 1024,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/4bff68a8-3d67-4942-8915-e9f07247a45f.jpg",
      "https://assets.runware.ai/assets/inputs/e88e1646-ae1a-4b54-97a1-469380a2cb66.jpg"
    ]
  }
}
```

---

### inpaint (inpaint)

![Mycology Benefit Supper Invitation](https://assets.runware.ai/examples/openai-gpt-image-2-6-flare/7cec3a21-cdef-461c-a65c-d083fe2e4bcc.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "23b36087-64ac-407d-b52a-e382550a9135",
  "model": "openai:gpt-image@2.6-flare",
  "positivePrompt": "The source image contains one king oyster mushroom on a continuous olive-green paper background. Replace the entire mushroom with a premium mushroom-shaped die-cut dinner invitation, preserving the surrounding background, landscape composition, camera angle, lighting, and natural lower-right cast shadow. Keep the new invitation within the approximate footprint and upright orientation of the original mushroom, with its front face fully visible.\n\nDesign the invitation as tactile uncoated bone-white cardstock with a broad rounded cap and sturdy stem silhouette. Use a sophisticated two-color risograph aesthetic: dense black botanical linework and warm persimmon-orange ink, with slight authentic ink misregistration and fine paper grain. Decorate the cap with scientifically observed chanterelles, fern tips, branching mycelium, and tiny spore-print dots arranged as an elegant symmetrical border. Avoid cartoon styling. The mood is intimate, scholarly, autumnal, and quietly eccentric.\n\nSet all invitation copy sharply and legibly in a refined editorial hierarchy, combining a condensed black serif display face with small uppercase sans-serif details. Include exactly this text:\n\nUNDERGROUND TABLE\nA BENEFIT SUPPER FOR THE\nCASCADIA MYCOLOGICAL ARCHIVE\n\nSATURDAY, OCTOBER 17, 2026\n6:30 PM\n\nFERN & FIR FIELD STATION\n44 MOSS ROAD · EUGENE, OREGON\n\nDINNER · FIELD NOTES · SPORE PRINT AUCTION\nRSVP BY OCTOBER 5\n\nMake “UNDERGROUND TABLE” the dominant headline across the cap, with the remaining information balanced down the stem. Maintain generous margins, strong typographic alignment, and print-ready clarity. Show only this single finished invitation lying on the existing background; no envelope, hands, utensils, extra mushrooms, loose stationery, logos, or added surrounding objects.",
  "width": 1280,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/7ce16a0f-bde7-4774-b92c-0ebe60cbebde.jpg"
    ],
    "maskImage": "https://assets.runware.ai/assets/inputs/9a6aa423-f961-42f1-9dda-3a4f965dd5f4.png"
  }
}
```

---

### transparent-background (transparent-background)

![Subsea Cable Robot Blog Hero](https://assets.runware.ai/examples/openai-gpt-image-2-6-flare/5f84d0aa-166a-47df-b936-11a6bcde6166.png)

```json
{
  "taskType": "imageInference",
  "taskUUID": "03a35abc-56cb-48c9-a8a3-ce6dd9c794f2",
  "outputFormat": "PNG",
  "model": "openai:gpt-image@2.6-flare",
  "positivePrompt": "Create one clearly defined standalone product: a compact remotely operated subsea robot engineered to inspect and repair undersea fiber-optic cables. Show the complete robot in a clean three-quarter front view, centered and filling roughly 80% of the square canvas, with every component fully inside the frame. Its integrated form includes a pressure-rated cobalt-blue body, acid-yellow protective frame, two folded precision manipulator arms, circular camera lenses, compact thrusters, and neatly routed black hydraulic lines. Premium photorealistic industrial product visualization with realistic anodized metal, painted aluminum, rubber, glass, subtle wear, crisp highlights, strong silhouette, and excellent readability at thumbnail size. Transparent background with clean antialiased edges and no environmental backdrop, ocean, seabed, water effects, bubbles, cable, platform, stand, shadow, border, lettering, numbers, labels, logos, or separate accessories. Exactly one robot.",
  "width": 1024,
  "height": 1024,
  "settings": {
    "background": "transparent"
  }
}
```

---

### text-to-gif (text-to-gif)

![Analog Seismograph Blog Hero](https://assets.runware.ai/examples/openai-gpt-image-2-6-flare/4ece18b7-5407-42d8-bf18-f735320a68d9.gif)

```json
{
  "taskType": "imageInference",
  "taskUUID": "9bcb21f1-d016-4073-a990-3302759a4e38",
  "outputFormat": "GIF",
  "model": "openai:gpt-image@2.6-flare",
  "positivePrompt": "Create a short, seamlessly looping animated editorial hero in a wide 16:9 composition. Subject: a vintage analog drum seismograph used in a mid-century geological observatory, shown in a clean three-quarter view against a simple warm parchment background. The instrument has a large horizontal cylinder wrapped in cream recording paper, a delicate black stylus touching the paper, a cast-metal frame, brass fittings and one small red calibration knob. One focused action only: the drum rotates through exactly one complete revolution while the stylus gently oscillates up and down, following a bold repeating earthquake waveform already wrapped around the paper. The motion ends at precisely the same drum orientation and stylus phase as the opening frame, with the waveform joining perfectly at the cylinder seam so the last frame transitions invisibly back to the first. Locked camera, no cuts, no zoom, no moving background elements. Make the mechanism and motion instantly readable at thumbnail size with a strong silhouette and restrained detail. Art direction: sophisticated screen-printed editorial illustration with crisp geometric shapes, subtle paper grain and slightly imperfect ink edges; limited palette of parchment cream, charcoal black, tobacco brown, muted brass and one vivid vermilion accent. Soft directional shadow beneath the machine. Calm, archival, tactile and technically credible. No people, text, numbers, labels, logos, interface elements or borders.",
  "settings": {
    "gif": {
      "frameCount": 8,
      "frameDuration": 0.12
    }
  }
}
```

---

### text-to-vector (text-to-vector)

![Urban Cooling Campaign Key Visual](https://assets.runware.ai/examples/openai-gpt-image-2-6-flare/8c94bd8b-c6ab-4bdb-b7dc-05e67e8aeff8.svg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "c440b96f-c4c4-445b-a0b2-95ed35f23573",
  "outputFormat": "SVG",
  "model": "openai:gpt-image@2.6-flare",
  "positivePrompt": "Create a finished vertical brand marketing campaign key visual for a company that manufactures modular public shade canopies for heat-stressed cities. Show one elegant cobalt-blue canopy as the unmistakable hero, spanning diagonally above a compact city plaza and casting a crisp geometric pool of cool shade. Within the blue shadow, a diverse group of commuters rests comfortably on integrated benches beside a drinking fountain, bicycle and small drought-tolerant tree; beyond the shadow, the surrounding pavement and simplified buildings glow with intense coral-orange heat. Use the contrast between the calm shaded refuge and the hot city as the central brand idea. Depict rising heat outside the shade with a few orderly concentric contour lines rather than realistic distortion. Art direction: premium contemporary vector illustration, deliberate flat shapes, clean confident contours, precise architectural geometry, controlled negative space, minimal texture, subtle screen-printed grain only in large color fields. Restricted palette of cobalt blue, sun-baked coral, warm cream, dark aubergine and one restrained chartreuse accent. Optimistic, civic-minded and design-forward rather than whimsical. Strong visual hierarchy, generous clear space in the upper-left area for campaign copy to be added later, composition adaptable to transit posters and social placements. No lettering, logo, signage, border, mockup, interface, photorealism, gradients, glossy 3D rendering or visual clutter.",
  "width": 1024,
  "height": 1280
}
```