Nano Banana is the Google Gemini image model that made the name. Write a description to generate a picture, or hand it a photo and say what to change — and see what the run costs before you commit to it.
Start from a written description, or from a photo you already have.
A simple per-image cost with no tier to weigh up first.
AI-generated reference frames picked to show the spread a general image model gets asked to cover — a painted scene, a composite that puts an impossible subject in a real landscape, and a traditional ink style. They illustrate the territory rather than being outputs captured from this specific model, and no prompt returns the same frame twice regardless.



Nano Banana is Google's Gemini image model, and the name most people mean when they say it is the one they want to try. It generates a picture from a written description and it edits a picture you supply, which between them covers most of what an image model gets asked to do. It is the first generation of a line that now runs to several members: Nano Banana 2 added multi-reference editing and resolution tiers, Nano Banana Pro sits above that for detail and type, and Nano Banana 2 Lite sits below as the light everyday tier.
Knowing which one you are on matters more than it sounds, because the newer members accept inputs this one does not. On Kavel it runs through a managed provider channel, the credit estimate shows before you generate, and a failed generation is refunded automatically unless it broke the content policy.
Creative engine
Choose text or photo input, describe what you want, and check the credit estimate before generating.
The first generation of Google's Gemini image line, and the version searches for 'Nano Banana' usually mean.
Generate from a description, or edit a photo you upload by describing the change.
Sits below Nano Banana 2 and Pro, which add multi-photo composites and higher resolution tiers.
Pick this one when the job is a single picture from a single input — a described scene, or one photo that needs one change. That is what it was built for and it does it without asking you to choose a tier first. The reason to move up is specific rather than general: go to Nano Banana 2 when you need several reference photos combined into one image or output above its range, to Nano Banana Pro when type has to stay legible and fine detail has to survive, and to Nano Banana 2 Lite when you want the same simple job at a flat cost that does not move with resolution.
One input, one output, one price — nothing to configure before you can see a result.
If you came looking for Nano Banana specifically, this is the model that name was attached to first.
Every limit here has a named model above it that removes exactly that limit.
What the original generation covers, and where the newer members of the family pick up.
Generate a picture from a written description with no source material.
Supply one photo and describe the change you want made to it.
Set the output shape to match where the image is going.
Credits come back automatically when a generation fails, unless it broke the content policy.
The generation parameters for this model, based on the provider spec it runs on here.
Four steps, whichever input you start from.
Generate from scratch, or start from a picture you already have.
Name the subject, the style and the light. For an edit, also name what must not change.
Choose the aspect ratio the finished image needs.
Confirm the estimate, run it, and download the result.
The jobs that do not need anything the newer models added.
One picture from one prompt, with no reference material to combine.
Edits that involve a single source image rather than a composite.
Run the same prompt here and on Nano Banana 2 or Pro to see what the newer tiers actually buy you.
The wording that works here carries across every other model in the line.
One credit pool covers Nano Banana images and Seedance and Veo video. The cost shows before every run, and failed jobs are not charged. Use a subscription for ongoing work, or a one-time pack when you just need to top up.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
One-time top-ups — buy extra credits any time you run low.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
What's included
Secure checkout by Stripe. Card details never touch our servers.
Charges appear as “KAVEL AI” on your card statement. You can cancel any time from Settings → Billing; cancellation takes effect at the end of the period you already paid for.
Powered by
Use one balance across every supported image and video model — ten of them today, listed below — and check the credit cost before each request.
Video models
Image models
Model credit guide
You're only charged for successful generations. The exact estimate in the generator varies by model, length, resolution, audio, and number of images.
| Type | Model | Credit cost |
|---|---|---|
| Video | Seedance 2.0 | 5s 720p image-to-video ≈ 188 credits; text-to-video ≈ 308 credits. Scales with resolution and length. |
| Video | Seedance 2 Fast | Faster and lower cost. 5s 720p text-to-video ≈ 248 credits. |
| Video | Seedance 2 Mini | The cheapest Seedance tier. 5s 720p ≈ 154 credits, 5s 480p ≈ 72 credits. |
| Video | Seedance 1.5 Pro | Audio doubles the rate. 5s 720p ≈ 27 credits silent, ≈ 53 with audio; 1080p ≈ 57 and ≈ 113. |
| Video | Veo 3.1 | Billed per video, not per second (Lite tier). About 45 credits at 720p and 53 at 1080p. |
| Video | Kling 3.0 | Audio raises the rate. 5s 720p ≈ 105 credits silent, ≈ 150 with audio; 1080p ≈ 135 and ≈ 203. |
| Video | MiniMax H3 | Fixed 2K, no resolution ladder. Priced per second — a 5s clip ≈ 158 credits. |
| Image | Nano Banana 2 | Generate or edit from text and images. About 8 credits per 1K image, 12 at 2K, 18 at 4K. |
| Image | Nano Banana Pro | Consistent run times across generations. About 12 credits per 1K or 2K image, 21 at 4K. |
| Image | Nano Banana 2 Lite | Faster, simpler variant. A flat 8 credits per image at every resolution. Start here to test. |
| Image | GPT Image 2 | The lowest-cost image model here. About 3 credits per 1K image, 6 at 2K, 12 at 4K. |
| Image | Seedream 5.0 Lite | Flat pricing — about 8 credits per image whether you generate or edit. |
Common questions about the original Nano Banana image model.
It is Google's Gemini image model. It generates pictures from a written description and edits a photo you supply. It is the first generation of a line that also includes Nano Banana 2, Nano Banana Pro and Nano Banana 2 Lite.
Nano Banana 2 accepts up to 14 reference photos in a single run, which makes composites and style transfer possible, and it offers 1K, 2K and 4K output with the cost rising by tier. The original handles one input at a time at a single rate.
Use this one for a single picture from a single input. Move to Nano Banana 2 when you need several photos combined, to Nano Banana Pro when type and fine detail have to hold up, and to Nano Banana 2 Lite for a flat cost that does not change with resolution.
Yes — supply one photo and describe the change. Name what should stay the same as well as what should change, or an edit can drift further than you wanted.
It is billed per generation at a single rate, with no resolution tiers to choose between. The estimate always shows before you generate, and failed generations cost nothing.
Check any generated image against your own use case and licence terms. If you supplied a source photo, the rights to that photo apply as well.
Open the generator, write a prompt or upload a photo, check the credits, and generate.
Start here, then step up to Nano Banana 2 or Pro when a job asks for more.