[Integrations](https://spiral.ai/integrations) › [Codex](https://spiral.ai/integrations/codex) › [GPT Image 2.5 Sunburst](https://spiral.ai/integrations/codex/gpt-image-2-5-sunburst)

# How to Use GPT Image 2.5 Sunburst in Codex

GPT Image 2.5 Sunburst creates campaign artwork, product concepts, and illustrations from written briefs. Unlike GPT Image 2.5 Sunburst Edit, it starts from text without a reference image.

|  |  |
| --- | --- |
| Model | GPT Image 2.5 Sunburst |
| Available through | OpenAI |
| Category | Image |
| Price | $0.0686 per 1024×1024 image at high quality ($0.00775 low, $0.0172 medium, $0.122 xhigh, $0.274 max). At high: $0.0536 at 1536×1024 or 1024×1536, $0.0486 at 1792×1024 or 1024×1792, $0.0509 at 512×512, $0.0465 at 256×256. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT Image 2.5 Sunburst in Codex

- Use GPT Image 2.5 Sunburst to create a 1536x1024 editorial illustration for the article in this project about urban gardening. Show a rooftop vegetable garden in a woodcut style, with no text and open space on the left for the page heading.
- Use GPT Image 2.5 Sunburst to create a 1024x1024 product concept based on the reusable bottle described in the project's product brief. Show brushed steel, a cork base, and soft window lighting. Include no lettering.
- Use GPT Image 2.5 Sunburst to create a 1536x864 presentation illustration from the project's onboarding brief. Show a paper airplane moving between three islands, with a restrained ink illustration style and no embedded text.
- Generate a product photo with GPT Image 2.5 Sunburst: a matte black water bottle on wet slate, soft morning light, 1:1. Tell me the price first. Save the result in ./assets.
- Make four logo concepts for a coffee brand called "Northline" with GPT Image 2.5 Sunburst.

## How to set up GPT Image 2.5 Sunburst in Codex

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**

```bash
codex mcp add spiral --url https://api.spiral.ai/mcp
```

2. **Sign in**: Codex opens the browser: sign in to Spiral and click Authorize. No API key. `codex mcp list` then shows Spiral.

```bash
codex mcp login spiral
```

### Use the Spiral skill

1. **Send Codex this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GPT Image 2.5 Sunburst**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openai",
    "model": "gpt-image-2.5-sunburst",
    "input": {
      "prompt": "A cute baby sea otter"
    }
  }'
```

Then paste one of the prompts above: Codex finds GPT Image 2.5 Sunburst on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/codex

## GPT Image 2.5 Sunburst tools and prices

- [GPT Image 2.5 Sunburst · Text to Image](https://spiral.ai/tools/openai/gpt-image-2.5-sunburst) (OpenAI): $0.0686 per 1024×1024 image at high quality ($0.00775 low, $0.0172 medium, $0.122 xhigh, $0.274 max). At high: $0.0536 at 1536×1024 or 1024×1536, $0.0486 at 1792×1024 or 1024×1792, $0.0509 at 512×512, $0.0465 at 256×256. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| n | 1 to 10 | 1 | The number of images to generate. Must be between 1 and 10. |
| size |  | auto | The size of the generated images. For `gpt-image-2`, `gpt-image-2-2026-04-21`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, and `gpt-image-2.5-flare-2026-09-08`, arbitrary resolutions are supported as `WIDTHxHEIGHT` strings, for example `1536x864`. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above `2560x1440` are experimental, and the maximum supported resolution is `3840x2160`. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes `1024x1024`, `1536x1024`, and `1024x1536` are supported by the GPT image models; `auto` is supported for models that allow automatic sizing. |
| quality | low, medium, high, xhigh, max, auto | auto | The quality of the image that will be generated. - `auto` (default value) will automatically select the best quality for the given model. - `high`, `medium` and `low` are supported for the GPT image models. - `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, also support `xhigh` and `max`. |
| background | transparent, opaque, auto | auto | Set the background of the generated image(s). This parameter is only supported for the GPT image models. Must be one of `transparent`, `opaque`, or `auto` (default value). When `auto` is used, the model will automatically determine the best background for the image. `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare`, including their `2026-09-08` snapshots, support `opaque` and `transparent` backgrounds. Transparent backgrounds are available for supported GPT Image models. For `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When using `transparent`, set the output format to `png` or `webp`. |
| output_format | png, jpeg, webp | png | The format in which the generated images are returned. This parameter is only supported for the GPT image models. Must be one of `png`, `jpeg`, or `webp`. |
| output_compression |  | 100 | The compression level (0-100%) for the generated images. This parameter is only supported for the GPT image models with the `webp` or `jpeg` output formats, and defaults to 100. |

## What can you do with GPT Image 2.5 Sunburst in Codex?

Turn project briefs into campaign artwork, product concepts, and illustrations that fit the app's visual direction. A coding agent can use project copy and layout dimensions to make the image brief specific.

### Campaign artwork

Create campaign artwork from a written brief or revise an existing campaign image. Specify the focal subject, lighting, headline space, and exact copy.

### Product scene concepts

Explore a product scene from a description or place a supplied product in a new setting. Describe materials, camera angle, and lighting; check product details before use.

### Presentation visuals

Create or revise a presentation illustration with a clear focal point and room for a slide title. Keep essential presentation text outside the image when exact typography matters.

### Editorial illustrations

Turn an article brief into an illustration or adapt existing artwork for a new story. Define the visual metaphor, medium, palette, and intended crop.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All Codex guides](https://spiral.ai/integrations/codex)

## GPT Image 2.5 Sunburst in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-image-2-5-sunburst)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-image-2-5-sunburst)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-image-2-5-sunburst)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-image-2-5-sunburst)
- [Cline](https://spiral.ai/integrations/cline/gpt-image-2-5-sunburst)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-image-2-5-sunburst)
- [Devin](https://spiral.ai/integrations/devin/gpt-image-2-5-sunburst)
- [dots](https://spiral.ai/integrations/dots/gpt-image-2-5-sunburst)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-image-2-5-sunburst)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-image-2-5-sunburst)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-image-2-5-sunburst)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-image-2-5-sunburst)
- [goose](https://spiral.ai/integrations/goose/gpt-image-2-5-sunburst)
- [Grok](https://spiral.ai/integrations/grok/gpt-image-2-5-sunburst)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-image-2-5-sunburst)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-image-2-5-sunburst)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-image-2-5-sunburst)
- [Manus](https://spiral.ai/integrations/manus/gpt-image-2-5-sunburst)
- [Muse](https://spiral.ai/integrations/muse/gpt-image-2-5-sunburst)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-image-2-5-sunburst)
- [n8n](https://spiral.ai/integrations/n8n/gpt-image-2-5-sunburst)
- [Notion](https://spiral.ai/integrations/notion/gpt-image-2-5-sunburst)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-image-2-5-sunburst)
- [opencode](https://spiral.ai/integrations/opencode/gpt-image-2-5-sunburst)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-image-2-5-sunburst)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-image-2-5-sunburst)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-image-2-5-sunburst)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-image-2-5-sunburst)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-image-2-5-sunburst)

## More Codex guides

- [GPT Image 2.5 Flare Text to Image](https://spiral.ai/integrations/codex/gpt-image-2-5-flare-text-to-image)
- [GPT Image 2.5 Sunburst Edit](https://spiral.ai/integrations/codex/gpt-image-2-5-sunburst-edit)
- [GPT Image 2.5 Flare Edit](https://spiral.ai/integrations/codex/gpt-image-2-5-flare-edit)
- [GPT Image 2.5 Sunburst Text to Image](https://spiral.ai/integrations/codex/gpt-image-2-5-sunburst-text-to-image)
- [GPT Image 2.5 Flare](https://spiral.ai/integrations/codex/gpt-image-2-5-flare)
- [GPT Image 2.6 Flare Edit](https://spiral.ai/integrations/codex/gpt-image-2-6-flare-edit)

## Questions about GPT Image 2.5 Sunburst in Codex

**Can Codex use GPT Image 2.5 Sunburst?**

Yes. Add Spiral to Codex as an MCP server, and Codex can find and run GPT Image 2.5 Sunburst like any built-in tool.

**How much does GPT Image 2.5 Sunburst cost in Codex?**

$0.0686 per 1024×1024 image at high quality ($0.00775 low, $0.0172 medium, $0.122 xhigh, $0.274 max). At high: $0.0536 at 1536×1024 or 1024×1536, $0.0486 at 1792×1024 or 1024×1792, $0.0509 at 512×512, $0.0465 at 256×256. Auto quality or size: the price of the one chosen for the request. Prompt: $6.50 per 1M tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.

**Do I need an OpenAI account to use GPT Image 2.5 Sunburst in Codex?**

No. Spiral runs GPT Image 2.5 Sunburst on its own OpenAI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GPT Image 2.5 Sunburst in Codex?**

About two minutes: add the hosted server, then sign in.

**Does Codex wait while GPT Image 2.5 Sunburst runs?**

GPT Image 2.5 Sunburst runs in the background. Codex starts the run, checks on it and gives you the image when it's ready.

**What is GPT Image 2.5 Sunburst good at?**

OpenAI recommends Sunburst for campaign creative and product imagery, especially work that needs careful visual control. Give it a concrete brief describing the subject, composition, lighting, and intended use.

**What image sizes can GPT Image 2.5 Sunburst produce?**

Custom dimensions must be multiples of 16, stay within a 1:3 to 3:1 aspect ratio, and contain 655,360 to 8,294,400 pixels, with neither edge above 3,840 pixels. Output above 2560x1440 is experimental.

**Can GPT Image 2.5 Sunburst make transparent images?**

Yes. Request a transparent background and choose PNG or WebP for assets you want to place over other designs.

**Can GPT Image 2.5 Sunburst put readable text in an image?**

Yes, but precise placement and clarity can still fail. Quote the exact wording, specify where it belongs, and check every word before using the result.

**How should I describe the image I want?**

Name the deliverable, then describe its subject, composition, visual style, and constraints. For visible text, provide the exact wording in quotes and describe its position.

