The AI models behind Cutlin
Cutlin brings its image models into one studio, on one credit balance. Pictures are made with GPT Image or Nano Banana 2.1, Fast or Quality. Video and vector models are coming soon.
- image models: GPT Image and Nano Banana
- 2
- speeds: Fast and Quality
- 2
- credit balance for every model
- 1

AI models, step by step
Write the prompt
Describe the picture you need, and pick its size in Configuration from one list, each size tagged with the platforms that use it.
Tick the models in Settings
Open Settings, the gear in the studio's header, and tick the picture models Cutlin may use - GPT Image 2.6 and Nano Banana 2.1, both ticked to begin with. It picks the best ticked one for each request, at the speed set in Configuration.
See what was used
Open a result's details to see each step that made it - reading the prompt, then making the picture - with its model, its tokens and its credits, along with the settings and the prompt.
Pictures: GPT Image or Nano Banana, Fast or Quality
Nano Banana 2.1 is Google's image model, strong on words in pictures, and it works from up to 14 pictures at once. GPT Image makes transparent backgrounds, which Nano Banana does not.
Each comes in two speeds. Fast is quicker and lighter on detail, for 5 credits a picture; Quality is slower and always works at its highest detail, for 15, whatever the picture's size. The studio's other settings - size and brand - do the rest.
You do not pick a model for each prompt. Settings lists the picture models, GPT Image 2.6 and Nano Banana 2.1, both ticked to begin with, and Cutlin picks the best ticked one for each request; untick one you would rather it did not use. Fast or Quality is set in Configuration.
Video and vectors: coming soon
Video and vector models are coming soon. Today, Cutlin makes pictures, posts and stories.
Every model on every plan
Plans differ only in their monthly credits, so every model is there whichever plan you are on. A picture uses 5 credits with Fast or 15 with Quality.
Every step, with its credits
A result's details list each AI call that made it, in order: reading the prompt with GPT-6 Luna, then making the picture. Each step shows its model, its tokens and its credits. Every AI result costs at least 1 credit; only the Watermark tool, which works in your browser without AI, is free.
AI models: the details
- Pictures
- GPT Image: Fast or Quality
- Pictures, Google
- Nano Banana 2.1: Fast or Quality
- Choosing
- Tick the models Cutlin may use in Settings; it picks the best ticked one
- Credits
- 5 per picture with Fast, 15 with Quality
Can I choose the model for pictures?
Yes. In Settings, tick the picture models Cutlin may use: GPT Image 2.6 or Nano Banana 2.1. It picks the best ticked one for each request. In Configuration, Speed is Auto, Fast - quick and 5 credits a picture - or Quality, the highest detail at 15.
Which model should I use?
Leave them all ticked and Cutlin picks for each request. To keep to Fast while you explore ideas, untick the Quality models, and tick them again for the version you publish. Only GPT Image makes a transparent background.
Are video and vector models coming soon?
Yes, they are coming soon. Today, Cutlin makes pictures, posts and stories.
Works well with
Create images
AI image generator
Text to image, Fast or Quality, at the size you need.
Video
AI video generator
Text to video, up to 30 seconds, in the shape you need.
Vectors
AI vector generator
Real, editable SVG from a text description.
Video
AI video editor
Change an MP4 or MOV of up to 30 seconds with a prompt.
People also ask
- Pricing and credits How many credits does an AI image cost? In Cutlin an AI image costs 5 credits with the Fast model and 15 with the Quality model, which always works at its highest detail, whatever the picture's size. A branded image, made with your brand guidelines and your real logo, costs 30. The cost is per picture, so four pictures from one prompt cost four times as much. Watermarking your pictures costs nothing.
- AI images How do I get better quality AI images? Give the AI more to work with, then make the final version properly. Write a specific prompt, attach reference pictures, ask for the size you will actually use, explore with a quick model and make the final picture with the most detailed one, refining with small follow-up changes. In Cutlin, Auto keeps to Fast while you explore; set Speed to Quality in Configuration, or ask for the most detail, for the final picture.
Try it on your next post
GPT Image or Nano Banana for pictures, Fast or Quality, on one credit balance.