infery
← All models

Nano Banana 2

nano-banana-2

Image generationby Google

Generate and edit images with Google's Nano Banana 2 (Gemini 3.1 Flash Image). Fast, high-quality image generation with multi-image reference support, conversational editing, and 14 aspect ratios.

images

Details

Accepts
text + image

Pricing

Input
62.5 cr / 1M tokens
Output
7500 cr / 1M tokens

Prices in credits (1 credit = $0.01).

Data schema

approximate

Input

FieldTypeDescription
nintegerHow many images to generate.
maskstringOptional mask for the edit; transparent pixels mark the area to change.
imagestringImage to edit — a URL, a data URI, or an artifact reference. Supplying one turns the call into an edit.
promptrequiredstringThe text prompt. Describes the image to generate, or the change to make when an image is supplied.
image_sizestringRequested output size.
aspect_ratiostringAspect ratio of the result, e.g. 16:9.
output_formatstringEncoding of the returned image.
resolutionenum: 1K, 2K, 4KResolution of the generated image. Higher resolutions take longer to generate.
image_inputarrayInput images to transform or use as reference (supports up to 14 images)
image_searchbooleanUse Google Image Search grounding to find web images as visual context for generation. When enabled, web search is also used automatically.
google_searchbooleanUse Google Web Search grounding to generate images based on real-time information (e.g. weather, sports scores, recent events).
seedThe seed for the random number generator.
pdf_urlOptional PDF document to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).
audio_urlOptional audio file to use as input context. Accepts an http(s)/data URL (downloaded and sent inline, max 15MB).
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.
video_urlOptional video to use as input context. Accepts an http(s)/data URL to a video file (downloaded and sent inline, max 15MB) or a YouTube URL (passed through to the model without downloading).
image_urlsarrayThe URLs of the images to use for image-to-image generation or image editing. Optional when at least one of `video_url`, `audio_url`, or `pdf_url` is provided.
num_imagesintegerThe number of images to generate.
system_promptstringOptional 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).
thinking_levelWhen set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.
safety_tolerancestringenum: 1, 2, 3, 4, 5, 6The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.
enable_web_searchbooleanEnable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.
limit_generationsbooleanExperimental 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.

Output

FieldTypeDescription
imagesarrayGenerated images ([{ url }]).