How to Use GPT Image 1 Mini Edit in Grok
Revise an existing image using written instructions and image references. Choose it for changes to a scene or subject; the text-to-image version creates an image from a written brief.
Prompts to try with GPT Image 1 Mini Edit in Grok
Copy an example into Grok, or ask in your own words.
Use GPT Image 1 Mini Edit on the image in this conversation. Change only the sofa upholstery to olive green. Preserve its shape, the room layout, lighting, and camera angle, and return a landscape image at 1536 × 1024 pixels.
Use GPT Image 1 Mini Edit on the mug image in this conversation. Remove the flowers painted on the mug and leave the ceramic plain white. Preserve the handle, proportions, lighting, and framing, and return a square PNG.
Remove the background from the photo I attach with GPT Image 1 Mini Edit and give me a transparent PNG.
Use GPT Image 1 Mini Edit to clean up these product shots so they sit on pure white.
Edit this image with GPT Image 1 Mini Edit: keep the subject, swap the background for a sunlit studio.
How to set up GPT Image 1 Mini Edit in Grok
Pick the way that suits you. Each takes about two minutes.
Use the Grok connector
- Add a custom connector
In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.
- Check that it is connected
Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.
Use the Spiral skill
- Send Grok this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run GPT Image 1 Mini Edit
One request; the result comes back by polling or a webhook.
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/edit", "input": { "prompt": "Dress the model in the clothes and hat. Add a cat to the scene and change the background to a Victorian era building.", "image_urls": [ "<image_urls>" ] } }'
Then paste one of the prompts above: Grok finds GPT Image 1 Mini Edit on Spiral, shows the price and runs it.
GPT Image 1 Mini Edit providers and prices
Spiral runs GPT Image 1 Mini Edit through fal. Open a card for today's price, with every fee included.
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
GPT Image 1 Mini Edit works from your prompt and image URLs. Ask Grok for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Image size | auto, 1024x1024, 1536x1024, or 1024x1536 | auto | Aspect ratio for the generated image |
| Background | auto, transparent, or opaque | auto | Background for the generated image |
| Quality | auto, low, medium, or high | auto | Quality for the generated image |
| Number of images | 1 to 4 | 1 | Number of images to generate |
| Output format | jpeg, png, or webp | png | Output format for the images |
Every API field of GPT Image 1 Mini · Edit is on its tool page: open its card above.
What can you do with GPT Image 1 Mini Edit in Grok?
Turn a written idea into artwork, or revise an image already in the conversation. Describe the subject and composition, then inspect the result before requesting another change.
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.
More on GPT Image 1 Mini Edit and Grok
Overview
GPT Image 1 Mini Edit in other agents
Questions about GPT Image 1 Mini Edit in Grok
Can Grok use GPT Image 1 Mini Edit?
Yes. Add Spiral to Grok as an MCP server, and Grok can find and run GPT Image 1 Mini Edit like any built-in tool.
How much does GPT Image 1 Mini Edit cost in Grok?
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 Grok plan is separate.
Do I need a fal account to use GPT Image 1 Mini Edit in Grok?
No. Spiral runs GPT Image 1 Mini Edit on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT Image 1 Mini Edit in Grok?
About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.
Does Grok wait while GPT Image 1 Mini Edit runs?
GPT Image 1 Mini Edit runs in the background. Grok 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.
Start using GPT Image 1 Mini Edit in Grok
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Grok:
set up https://spiral.ai/SKILL.md


