Models / Nano Banana 2
Google · Image

Nano Banana 2

Nearly Google’s best tool at half the price, and it takes fourteen reference pictures in one go. Made by Google. From $0.066 an image.

nano-banana-2
TypeImage
InputsText, References, Video, Audio
Resolution0.5K, 1K, 2K, 4K
Aspect ratioauto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8
From$0.066 / image
UpdatedOct 12, 2026

Pricing

SettingMiniAPIfalDifference
2K$0.132 / image$0.12+10%
4K$0.176 / image$0.16+10%
0.5K$0.066 / image$0.06+10%
1K$0.088 / image$0.08+10%

Parameters

NameRequiredValuesDefaultDescription
promptYestextWhat to make, in plain words.
audio_urlNohttps URLThe sound to use.Only with edit
pdf_urlNohttps URLOptional PDF document to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).Only with edit
video_urlNohttps URLThe clip to work on.Only with edit
image_urlsNohttps URLsPictures to use as references.Only with edit
num_imagesNo1 to 41How many images to make. Each one is charged.
aspect_ratioNoauto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8autoShape of the result, for example 16:9 or 9:16.
output_formatNojpeg, png, webppngFile type of the result.
safety_toleranceNo1 to 64How strict the model's own content filter is. Lower is stricter.
system_promptNotextOptional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).
resolutionNo0.5K, 1K, 2K, 4K1KOutput size. Higher is sharper, slower and costs more.
limit_generationsNotrue, falsetrueExperimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.
enable_web_searchNotrue, falsefalseEnable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.
thinking_levelNominimal, highWhen set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.
seedNointegerThe same seed with the same settings gives a similar result. Leave it out for a random one.

Quickstart

curl -X POST "https://api.minicut.ai/v1/queue/nano-banana-2" \
  -H "Authorization: Key $MINIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red fox in fresh snow, morning light","resolution":"0.5K"}'
200 OK
{
  "request_id": "0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "status": "IN_QUEUE",
  "queue_position": 0,
  "status_url": "https://api.minicut.ai/v1/queue/nano-banana-2/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/nano-banana-2/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/nano-banana-2/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "0.066000",
  "currency": "USD"
}

FAQ

How much does Nano Banana 2 cost?

From $0.066 per image at 0.5K. Pricing lists every setting.

What inputs does Nano Banana 2 take?

Text, References, Video, Audio.

Am I charged if a Nano Banana 2 job fails?

No. You are not charged for it.

Related models

All 74 models