Public Model / nano-banana

Nano Banana 2 API pricing

Image creation and editing across 1K through 4K with multi-image reference support.

New to this model family? Compare Nano Banana models and generate your first image with Python.

Availability
Available
Tasks
Create Image, Edit Image
Published rates from
$0.04

Request calculator

Configure Nano Banana 2

Controls and rates come directly from the checked public catalog.

Interactive calculator

Price a direct generation

Choose a task, configure its inputs, and see the current catalog price.

Step 1

Choose a generation type

Step 2

Configure generation

Model
Nano Banana 2
Resolution1K
Outputs1

Step 3

Reference total

$0.041 output at $0.04 each
Generation
$0.041 image x $0.04
Minimum request
$0.04
Get started

The API estimate for your exact request is authoritative before paid work starts.

Best fit

Use Nano Banana 2 for flexible image workflows that need a wide resolution range and several source images.

Use cases

  • Multi-reference compositions
  • Resolution-specific campaign exports

Know before building

  • Up to 14 reference images are included. Choose PNG or JPEG at the same price; output resolution determines the price.

Generated contract

Tasks, controls, and rates

Published rates

image.create
Varies by resolution
$0.04 / image$0.04 minimum
image.edit
Varies by resolution
$0.04 / image$0.04 minimum

Request controls

image.createAspect ratioauto · 1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9 · 1:4 · 4:1 · 1:8 · 8:1
image.createOutput formatpng · jpeg
image.createPromptText input
image.createReference imagesUp to 14 items
image.createResolution1K · 2K · 4K
image.editAspect ratioauto · 1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9 · 1:4 · 4:1 · 1:8 · 8:1
image.editImagesUp to 14 items
image.editOutput formatpng · jpeg
image.editPromptText input
image.editResolution1K · 2K · 4K

Lifecycle: queued -> running -> succeeded -> failed -> cancelled -> manual_review

Output fields: assets

Runnable examples

Estimate first, then create

Both requests use the same normalized task, model, and input payload. Creating work requires an API key and idempotency key.

1. Estimate

curl https://api.entirefeed.com/v1/estimate \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
  "task": "image.create",
  "model": "nano-banana-2",
  "input": {
    "aspect_ratio": "auto",
    "output_format": "png",
    "resolution": "1K",
    "prompt": "Combine the reference products into a clean editorial flat lay"
  }
}'

2. Create

curl https://api.entirefeed.com/v1/generations \
  -X POST \
  -H "Authorization: Bearer $ENTIREFEED_API_KEY" \
  -H "Idempotency-Key: nano-banana-2-example-001" \
  -H "Content-Type: application/json" \
  -d '{
  "task": "image.create",
  "model": "nano-banana-2",
  "input": {
    "aspect_ratio": "auto",
    "output_format": "png",
    "resolution": "1K",
    "prompt": "Combine the reference products into a clean editorial flat lay"
  }
}'