[Integrations](https://spiral.ai/integrations) › [dots](https://spiral.ai/integrations/dots) › [GPT Image 1 Mini](https://spiral.ai/integrations/dots/gpt-image-1-mini)

# How to Use GPT Image 1 Mini in dots

Create illustrations, game assets, and image concepts from a written brief. Choose this version when you want a new image; the Edit version starts from reference images.

|  |  |
| --- | --- |
| Model | GPT Image 1 Mini |
| Available through | fal |
| Category | Image |
| Price | Up to $0.0676 per run at the default inputs. `quality`: auto (default) $0.0676, low $0.0078, medium $0.0195, high $0.0676. $0.0676 per unit of `num_images`. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with GPT Image 1 Mini in dots

- Every Monday, use GPT Image 1 Mini to create one 1536 × 1024 illustration for a gardening newsletter. This week's subject is seedlings on a sunny windowsill. Use pencil and watercolor, leave the right third clear for later text, and keep the image free of lettering.
- Each morning, use GPT Image 1 Mini to create a square illustration of one breakfast ingredient for a cooking lesson. Start with a whole lemon and a cut lemon on a white plate. Use a white background, natural window light, and no labels.
- Every Friday, use GPT Image 1 Mini to create a 1024 × 1536 reading poster draft. Show a child reading beside a sleeping dog in a warm pencil illustration, leave the top quarter empty, and add no text.
- Each week, use GPT Image 1 Mini to create a transparent square PNG of one camping object for a game concept review. Start with a rolled canvas sleeping bag, show the entire object from a three-quarter angle, and include no words or scenery.
- Every Tuesday, use GPT Image 1 Mini to create a 1536 × 1024 illustration for a repair workshop. Start with hands mending a torn jacket at a worktable. Use a limited rust, navy, and white palette, and leave the upper left clear for a title added later.

## How to set up GPT Image 1 Mini in dots

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

### Use the Spiral skill

1. **Send dots 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 Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for your dot. Copy it.

2. **Send your dot this message**: Your dot reads Spiral's skill and asks for your API key.

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

3. **Give your dot the key**: When your dot asks for the key, add it where your dot keeps secrets, never in the chat itself.

### 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 1 Mini**: 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": "fal",
    "model": "fal-ai/gpt-image-1-mini",
    "input": {
      "prompt": "A serene landscape with mountains reflecting in a crystal-clear lake at sunset, photorealistic style"
    }
  }'
```

Then paste one of the prompts above: dots finds GPT Image 1 Mini on Spiral, shows the price and runs it.

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

## GPT Image 1 Mini tools and prices

- [GPT Image 1 Mini · Text to Image](https://spiral.ai/tools/fal/fal-ai/gpt-image-1-mini) (fal): Up to $0.0676 per run at the default inputs. `quality`: auto (default) $0.0676, low $0.0078, medium $0.0195, high $0.0676. Per unit of `num_images`: auto (default) $0.0676, low $0.0078, medium $0.0195, high $0.0676.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size | auto, 1024x1024, 1536x1024, 1024x1536 | auto | Aspect ratio for the generated image |
| background | auto, transparent, opaque | auto | Background for the generated image |
| quality | auto, low, medium, high | auto | Quality for the generated image |
| num_images | 1 to 4 | 1 | Number of images to generate |
| output_format | jpeg, png, webp | png | Output format for the images |

## What can you do with GPT Image 1 Mini in dots?

Prepare recurring illustration drafts from a scheduled brief. Keep the visual instructions explicit and review each batch for text errors, misplaced objects, and changes to recurring subjects.

### Game asset concepts

Try a square inventory illustration of a single object with a transparent background. Review its silhouette at the size it will appear in the game.

### Editorial illustrations

Turn an article's main idea into a landscape illustration. Specify the subject and visual medium, and leave space for a headline added separately.

### Scene revisions

Use Edit to try a different object color or background in an existing image. State which details should stay, then check for unintended changes.

### Portrait artwork

Create a 1024 × 1536 illustration for a cover concept or poster. Keep exact typography as a separate design task.

### Visual direction studies

Describe the same subject in watercolor, paper collage, and pencil. Compare the results before choosing a direction for the finished artwork.

### Product image variations

Use a product image as an editing reference to explore a different setting. Inspect the product's shape and labels before accepting the result.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All dots guides](https://spiral.ai/integrations/dots)

## GPT Image 1 Mini in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-image-1-mini)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-image-1-mini)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-image-1-mini)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-image-1-mini)
- [Cline](https://spiral.ai/integrations/cline/gpt-image-1-mini)
- [Codex](https://spiral.ai/integrations/codex/gpt-image-1-mini)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-image-1-mini)
- [Devin](https://spiral.ai/integrations/devin/gpt-image-1-mini)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-image-1-mini)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-image-1-mini)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-image-1-mini)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-image-1-mini)
- [goose](https://spiral.ai/integrations/goose/gpt-image-1-mini)
- [Grok](https://spiral.ai/integrations/grok/gpt-image-1-mini)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-image-1-mini)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-image-1-mini)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-image-1-mini)
- [Manus](https://spiral.ai/integrations/manus/gpt-image-1-mini)
- [Muse](https://spiral.ai/integrations/muse/gpt-image-1-mini)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-image-1-mini)
- [n8n](https://spiral.ai/integrations/n8n/gpt-image-1-mini)
- [Notion](https://spiral.ai/integrations/notion/gpt-image-1-mini)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-image-1-mini)
- [opencode](https://spiral.ai/integrations/opencode/gpt-image-1-mini)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-image-1-mini)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-image-1-mini)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-image-1-mini)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-image-1-mini)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-image-1-mini)

## More dots guides

- [Finegrain Eraser Mask](https://spiral.ai/integrations/dots/finegrain-eraser-mask)
- [GPT Image 1 Mini Edit](https://spiral.ai/integrations/dots/gpt-image-1-mini-edit)
- [Finegrain Eraser Bbox](https://spiral.ai/integrations/dots/finegrain-eraser-bbox)
- [GPT Image 1.5](https://spiral.ai/integrations/dots/gpt-image-1-5)
- [Finegrain Eraser](https://spiral.ai/integrations/dots/finegrain-eraser)
- [GPT Image 1.5 Edit](https://spiral.ai/integrations/dots/gpt-image-1-5-edit)

## Questions about GPT Image 1 Mini in dots

**Can dots use GPT Image 1 Mini?**

Yes. Add Spiral to dots as an MCP server, and dots can find and run GPT Image 1 Mini like any built-in tool.

**How much does GPT Image 1 Mini cost in dots?**

Up to $0.0676 per run at the default inputs. `quality`: auto (default) $0.0676, low $0.0078, medium $0.0195, high $0.0676. $0.0676 per unit of `num_images`. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your dots plan is separate.

**Do I need a fal account to use GPT Image 1 Mini in dots?**

You need no fal account. dots uses one Spiral API key for every tool, and Spiral runs GPT Image 1 Mini on its own fal account.

**How long does it take to set up GPT Image 1 Mini in dots?**

About two minutes: create an API key, then send your dot this message, then give your dot the key.

**Does dots wait while GPT Image 1 Mini runs?**

GPT Image 1 Mini runs in the background. dots starts the run, checks on it and gives you the image when it's ready.

**What is the difference between GPT Image 1 Mini and GPT Image 1 Mini Edit?**

The generation version creates a new image from a written prompt. Edit uses existing images as references alongside your instructions.

**What image sizes can it produce?**

Use 1024 × 1024 pixels for square images, 1536 × 1024 for landscape, or 1024 × 1536 for portrait.

**Can it make images with transparent backgrounds?**

Yes. Request a transparent background and save the result as PNG or WebP.

**Can I trust text inside the generated image?**

Check every word and its placement before using the image. For artwork that needs exact typography, consider generating the illustration first and adding the text in your design tool.

**Will a character look identical across several images?**

Separate generations can change a character's appearance or brand details. Try editing an approved reference, then compare each result against it.

