# GPT Image 2.6 Sunburst

> Run GPT Image 2.6 Sunburst by openai online or via API. $30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out, no setup.

**URL:** https://inference.sh/apps/openai/gpt-image-2-6-sunburst
**Last updated:** 2026-11-05

---

OpenAI's GPT Image 2.6 for detailed visual work. Text-to-image, edits with masks or markup, complexity control, transparent backgrounds, SVG and animated GIF output.

- app: `openai/gpt-image-2-6-sunburst`
- maker: [openai](https://inference.sh/apps/openai.md)
- category: [image](https://inference.sh/apps/category/image.md)
- input → output: text → image
- tasks: [text to image](https://inference.sh/apps/tag/text-to-image.md), [image editing](https://inference.sh/apps/tag/image-editing.md)
- price: $30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out
- runs via: api, javascript and python sdk, belt cli, mcp

## gpt-image-2-6-sunburst API Guide

### About
openai's gpt image 2.6 for detailed visual work. text-to-image, edits with masks or markup, complexity control, transparent backgrounds, svg and animated gif output.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @2wg1by5s pinned
result = client.run({
        "app": "openai/gpt-image-2-6-sunburst@2wg1by5s",
        "input": {
            "prompt": "A cat wearing a tiny top hat, oil painting style"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @2wg1by5s pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "openai/gpt-image-2-6-sunburst@2wg1by5s",
        "input": {
            "prompt": "A cat wearing a tiny top hat, oil painting style"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "openai/gpt-image-2-6-sunburst@2wg1by5s",
        "input": {
            "prompt": "A cat wearing a tiny top hat, oil painting style"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "openai/gpt-image-2-6-sunburst@2wg1by5s",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **prompt** (string) *required*: Text prompt describing the desired image. For gif output, describe the subject, motion and loop.
- **images** (array): Optional image(s) to edit. A mask or markup applies to the first image; the others serve as references.
- **mask** (string): Optional mask for the first image. Its transparent areas mark where to edit. Cannot be combined with markup.
- **markup** (string): Optional transparent PNG with circles, sketches or other annotations showing where to edit. Must match the first image's dimensions. Cannot be combined with mask.
- **width** (integer): Output width in pixels. Must be a multiple of 16. For gif this is the frame width; leave width and height unset to let the model pick a size that fits the frame count.
- **height** (integer): Output height in pixels. Must be a multiple of 16. For gif this is the frame height; leave width and height unset to let the model pick a size that fits the frame count.
- **quality** (string): Rendering quality. 'low' for drafts, 'high' for final assets, 'xhigh' and 'max' for maximum detail at higher cost. For svg, sets the reference image's quality.
- **complexity** (string): How much the model plans before rendering, independent of quality and at no extra cost. Lower suits focused edits; higher helps dense text and complex layouts but adds latency.
- **n** (integer): Number of images to generate (1-10). svg output requires 1.
- **output_format** (string): Output file format. gif (animated) and svg (vector) are for generation only, not edits.
- **output_compression** (integer): Compression level for jpeg/webp (0-100). Ignored for other formats.
- **frame_count** (integer): Number of animation frames. Used only for gif output.
- **frame_duration_ms** (integer): Delay per animation frame in milliseconds, rounded to 10 ms. Used only for gif output.
- **moderation** (string): Content moderation strictness. 'auto' applies standard filtering; 'low' is less restrictive.
- **background** (string): Background transparency. 'transparent' requires png or webp output; prompt for an isolated subject. 'opaque' forces a solid background.

#### Output
- **images** (array): The generated image files.

## other image apps

- [GPT Image 2.6 Flare](https://inference.sh/apps/openai/gpt-image-2-6-flare.md): $30.00/M output, $5.00/M text input, $8.00/M image input, $0.10/M SVG input, $0.50/M SVG output
- [Gemini Nano Banana 2.1](https://inference.sh/apps/google/gemini-nano-banana-2-1.md): $1.50/M input, $0.0336–$0.1134/image (1K–4K), +$0.014/query Google Search
- [Grok Imagine Image 2.0](https://inference.sh/apps/xai/grok-imagine-image-2-0.md): $0.04/img low 1k, $0.06/img low 2k, $0.06/img med 1k, $0.08/img med 2k; $0.01/source img (edits)
- [GPT Image 2.5 Sunburst](https://inference.sh/apps/openai/gpt-image-2-5-sunburst.md): $0.006-$0.21 per 1024x1024 image: low $0.006, medium $0.013, high $0.053, xhigh $0.094, max $0.21. Larger sizes cost more; edits add ~$0.008 per reference image.
- [GPT Image 2.5 Flare](https://inference.sh/apps/openai/gpt-image-2-5-flare.md): $0.006-$0.21/image at 1024x1024: low $0.0059, medium $0.0132, high $0.0527, xhigh $0.0937, max $0.2107. Larger sizes cost more; edits add ~$0.0083 per reference image.

## faq

### how much does GPT Image 2.6 Sunburst cost?

$30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out. you pay per run from your inference shell credits. no subscription is required.

### how do I run GPT Image 2.6 Sunburst via api?

call openai/gpt-image-2-6-sunburst with the javascript or python sdk, the rest api, or `belt app run openai/gpt-image-2-6-sunburst` from a terminal. the api reference on this page lists every input.

### who makes GPT Image 2.6 Sunburst?

GPT Image 2.6 Sunburst is made by openai and runs on inference shell. every openai app is listed at https://inference.sh/apps/openai.

### can my agent use GPT Image 2.6 Sunburst?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to GPT Image 2.6 Sunburst?

other image apps on inference shell include GPT Image 2.6 Flare, Gemini Nano Banana 2.1, Grok Imagine Image 2.0, GPT Image 2.5 Sunburst. they run through the same api, so switching is a one-line change.