How to Use MAI Image 2.5 in ChatGPT
Use MAI Image 2.5 for product imagery, realistic scenes, and posters with text inside the image. It is the base model in the 2.5 series; Pro adds higher fidelity for demanding artwork.
Prompts to try with MAI Image 2.5 in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use MAI Image 2.5 to make a square product photograph of an amber glass soap bottle on pale stone. Use soft light from the right, visible glass reflections, and the label text "CEDAR" centered on the bottle.
Create a vertical poster with MAI Image 2.5 for a pottery workshop. Show clay-covered hands shaping a bowl, warm afternoon light, and the words "MAKE WITH CLAY" across the top. Use a three-to-four shape.
Use MAI Image 2.5 to create a wide editorial photograph of a quiet neighborhood bakery before opening. Show flour on a wooden counter, warm interior light, and blue morning light through the window. Leave room on the right for a caption.
Make a square packaging concept with MAI Image 2.5 for a fictional tea called "FIELD NOTES". Show a cream paper box, a botanical illustration, dark green lettering, and soft studio lighting. Check the visible wording afterward.
Use MAI Image 2.5 to create a landscape presentation image of a shared urban garden. Show raised beds, a watering can, and late-afternoon sunlight. Keep the upper-left area uncluttered for a slide title.
How to set up MAI Image 2.5 in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT 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 MAI Image 2.5
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": "microsoft/mai-image-2.5", "input": { "prompt": "A photorealistic concept-art poster of a university campus at sunset, cinematic lighting, a banner reading \"LOUISVILLE\" in bold serif type." } }'
Then paste one of the prompts above: ChatGPT finds MAI Image 2.5 on Spiral, shows the price and runs it.
MAI Image 2.5 providers and prices
Spiral runs MAI Image 2.5 through fal. Open a card for today's price, with every fee included.
Up to $0.078 per run at the default inputs. $0.078 per unit of num_images.
Settings you can ask for
MAI Image 2.5 works from your prompt. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Number of images | 1 to 4 | 1 | The number of images to generate. |
| Aspect ratio | auto, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, or 2:3 | auto | The aspect ratio of the generated image. Use "auto" to let the model decide based on the prompt. |
| Output format | jpeg, png, or webp | png | The format of the generated image. |
Every API field of Mai Image 2.5 Text to Image is on its tool page: open its card above.
What can you do with MAI Image 2.5 in ChatGPT?
Turn a written idea into a product shot, poster, or realistic scene. A chat app can help you define the composition and compare the generated image with your brief.
Product campaign concepts
Create a product scene with a specific material, camera angle, and light source. Use it to compare visual directions before commissioning final photography.
Posters with embedded text
Explore event posters or packaging concepts with quoted headlines and explicit text placement. Review every word before using the artwork.
Realistic editorial illustrations
Generate a scene for an article or presentation by describing its subject, setting, lighting, and mood. Use the result as an illustration and check any factual details.
Brand imagery
Turn a written creative brief into image concepts with defined colors, materials, and composition. Keep those directions explicit when comparing alternatives.
Presentation visuals
Create a realistic scene with a deliberately open area for slide copy. Describe the image composition separately from any words you want rendered inside it.
Packaging studies
Explore how a fictional product could look with different materials, label layouts, and lighting. Quote the label wording and inspect the resulting typography.
More on MAI Image 2.5 and ChatGPT
Overview
MAI Image 2.5 in other agents
Questions about MAI Image 2.5 in ChatGPT
Can ChatGPT use MAI Image 2.5?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run MAI Image 2.5 like any built-in tool.
How much does MAI Image 2.5 cost in ChatGPT?
Up to $0.078 per run at the default inputs. $0.078 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 ChatGPT plan is separate.
Do I need a fal account to use MAI Image 2.5 in ChatGPT?
No. Spiral runs MAI Image 2.5 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up MAI Image 2.5 in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while MAI Image 2.5 runs?
MAI Image 2.5 runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
What is MAI Image 2.5 good at?
Start with product shots, realistic scenes, and promotional artwork. Lighting, reflections, and text inside posters or packaging are documented strengths.
Can MAI Image 2.5 put readable text in an image?
Yes. Microsoft specifically documents labels, posters, packaging, and signage as supported text-rendering uses. Check the wording before publishing.
What is its maximum image resolution?
The model card specifies a maximum area of 1,048,576 pixels, equivalent to 1024 × 1024 for a square image. Plan larger deliverables around that pixel budget.
How should I write a prompt?
Describe the subject, camera view, lighting, layout, and mood. Put any words that should appear inside the image in quotation marks and state where they belong.
What should I check in the output?
Check visual details against your brief, especially anything readers might treat as factual. Microsoft warns that plausible-looking details can still be inaccurate or misleading.
Start using MAI Image 2.5 in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


