Nano Banana
Google's Nano Banana is a fast, low-cost image generation and editing model. Supports text-to-image and reference-based image editing with up to 14 reference images. Best for high-volume creative iteration.
Optional input images to edit or use as reference (up to 14). Leave empty for pure text-to-image.
Aspect Ratio
Aspect ratio of the generated image. 'auto' lets the model choose from your prompt and inputs.
Your result renders here.
Use Nano Banana via the API
Generate with Nano Banana from your own code. Async by design: submit a generation, get a run id back instantly, poll until it completes. Billed in credits at the best available provider price — from $0.039 per image.
1 — Start a generation
curl -X POST https://app.scenetra.com/api/v1/generate/nano-banana \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"a watercolor fox in falling snow, soft light","aspect_ratio":"1:1"}'Response (202)
{
"runId": "run_abc123",
"status": "PENDING",
"model": "nano-banana",
"estimatedCredits": 39,
"statusUrl": "/api/v1/runs/run_abc123"
}2 — Poll until COMPLETED (every 2-5 seconds)
curl https://app.scenetra.com/api/v1/runs/run_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"Response
{
"runId": "run_abc123",
"status": "COMPLETED",
"progress": { "completed": 1, "total": 1 },
"outputs": [
{ "type": "image", "url": "https://images.scenetra.com/..." }
],
"error": null,
"estimatedCredits": 39
}Request fields
| Field | Type | Description | Default |
|---|---|---|---|
| prompt* | string | Describe the image to generate, or the edit to apply to the input images. | — |
| image_urls | string[] (https URLs) | Optional input images to edit or use as reference (up to 14). Leave empty for pure text-to-image. | — |
| aspect_ratio | string | Aspect ratio of the generated image. 'auto' lets the model choose from your prompt and inputs.auto · 21:9 · 16:9 · 3:2 · 4:3 · 1:1 · 3:4 · 2:3 · 9:16 | auto |
| callbackUrl | string (https URL) | Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth. | |
Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.
Good to know
Billing
Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.
Errors
Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.
What makes Nano Banana different
The original viral editor, still the cheapest
Nano Banana is the Gemini 2.5 Flash image model that made reference-based AI photo editing mainstream — and at a flat $0.039 per image it remains the cheapest tier in the family. When you need twenty variations, not one perfect render, this is the model that keeps the bill in coffee money territory.
Reference-based editing with up to 14 images
Attach up to 14 reference images and describe the change: swap a background, restyle a subject, keep a character consistent across a whole set. References can be uploads or outputs of other nodes on your Scenetra board, so edit chains — generate, edit, edit again — are just connected nodes.
Flat pricing, zero mental math
Every Nano Banana generation costs the same $0.039. No per-megapixel formulas and no resolution multipliers to reason about — which is exactly what you want for batch work, where predictable unit cost matters more than headline resolution.
A clean upgrade path
Because all three Nano Banana tiers live on the same Scenetra board, the original is a natural drafting layer: explore prompts here at $0.039, then re-run the keeper on Nano Banana 2 for higher-resolution output or Nano Banana Pro for maximum fidelity and in-image text. Same prompt, same canvas, different node.
Parameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Describe the image to generate, or the edit to apply to the input images. | — |
| Input Images | image upload | Optional input images to edit or use as reference (up to 14). Leave empty for pure text-to-image. | — |
| Aspect Ratio | select | Aspect ratio of the generated image. Auto lets the model choose from your prompt and inputs.auto · 21:9 · 16:9 · 3:2 · 4:3 · 1:1 · 3:4 · 2:3 · 9:16 | auto |
Pricing
From $0.039 per image
Pay per generation — only pay for what you use.
Per image
$0.039
per image
What a video costs
| Duration | Per generation |
|---|---|
| 1 image (default settings) | $0.04 |
| 4 images (4 generations) | $0.16 |
| 25 images (25 generations) | $0.98 |
Use cases
Rapid ideation
- Dozens of concepts for pennies
- Prompt exploration rounds
- Style tests before final renders
- Quick client mockups
Social content
- Daily post visuals
- Fast meme-style edits
- Profile and banner art
- Story and reel stills
E-commerce at volume
- Bulk listing imagery
- Background swaps
- Simple product variants
- Placeholder art for catalogs
Photo editing
- Reference-guided retouches
- Subject and object swaps
- Style transfers
- Character consistency sets
Frequently asked questions
What is Nano Banana?+
Nano Banana is Google's Gemini 2.5 Flash image model — the original of the Nano Banana family, famous for fast, natural-language photo editing. It handles text-to-image generation and reference-based editing with up to 14 images, and on Scenetra it runs as a node in the visual workflow editor.
Is Nano Banana free?+
No — the model is paid. On Scenetra it's $0.039 per image, paid per generation from your credit balance — no subscription required and nothing to cancel.
How much does Nano Banana cost?+
A flat $0.039 per image on Scenetra. That makes it the cheapest tier in the Nano Banana family; Nano Banana 2 and Nano Banana Pro cost more per image.
Which version of Nano Banana is the best?+
It depends on the job. The original Nano Banana is the cheapest and great for volume and quick edits. Nano Banana 2 adds higher resolutions up to 4K and the newest Flash engine while staying inexpensive. Nano Banana Pro delivers the highest fidelity and the best in-image text, at a premium. On Scenetra all three sit on one board, so you can run the same prompt through each and judge for yourself.
Can Nano Banana edit photos with reference images?+
Yes — that's its signature strength. Attach up to 14 reference images and describe the edit in plain language: background swaps, style changes, subject consistency across a series. Leave the references empty and it behaves as a pure text-to-image model.
What's the difference between Nano Banana and Nano Banana 2?+
Nano Banana 2 runs on the newer Gemini 3.1 Flash engine and generates from 512px up to native 4K, priced higher per image. The original is flat $0.039 per image and is best treated as the 1K-class volume tier. If you're producing final assets at high resolution, use 2 or Pro; if you're iterating, the original is hard to beat on cost.
Related models
Nano Banana 2
Generate high-quality images at up to 4K resolution using Google's Gemini 3.1 Flash model. Nano Banana 2 is optimized for speed, supports text-to-image and image editing with reference images, and offers flexible aspect ratios.
View model →Nano Banana Pro
The professional tier of Google's Gemini-powered image generation. Nano Banana Pro delivers higher quality outputs with support for up to 4K resolution, flexible aspect ratios, multiple output formats, and image editing with reference images.
View model →Z-Image Turbo
A blazing-fast text-to-image model with high quality outputs and customizable acceleration. Z-Image Turbo generates images in as few as 1-8 inference steps, making it ideal for rapid prototyping and real-time creative workflows.
View model →Start creating with Nano Banana
Use Nano Banana alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started