Gemini Nano Banana 2.1

Gemini Nano Banana 2.1 is optimized for multimodal image generation and editing and offers a balance of price and performance.

Note: The seed, topK, logprobs, temperature, and topP parameters aren't supported for Nano Banana 2.1. Setting any of these parameters returns an API error.

Try in Agent Studio View in Model Garden Deploy example app Pricing

Note: "Deploy example app" requires a Google Cloud project with billing and Agent Platform API enabled.

Model ID	gemini-nano-banana-2.1
Modalities	description Text Input and output photo Image Input and output mic_off Audio Not supported videocam Video Input only
Token limits	Context window	131,072
	Maximum output tokens	32,768
Capabilities	Thinking Supported System instructions Supported Structured output Not supported Context caching Implicit context caching Supported RAG Engine Not supported Tuning Not supported URL context Not supported Image generation Image generation, Image generation from video input Supported Edit images Edit images, Multi-turn image editing Supported Interleaved images and text Supported Content Credentials (C2PA) Supported Virtual try-on Supported Person generation Supported
Tools	Grounding Google Search, Image search Supported Code execution Not supported Function calling Not supported
Consumption options	Provisioned Throughput Supported Batch inference Supported Pay-as-you-go Standard PayGo Supported Fixed quota Not supported
Input size limit	500 MB
Technical specifications	Image	Maximum images per prompt: 14 Maximum file size per file for inline data or direct uploads through the console: 7 MB Maximum file size per file from Google Cloud Storage: 30 MB Maximum number of output images per prompt: Limited to 32,768 output tokens Supported aspect ratios: 1:1, 3:2, 2:3, 3:4, 1:4, 4:1, 4:3, 4:5, 5:4, 1:8, 8:1, 9:16, 16:9, 21:9, 9:21 Supported resolutions: 1K, 2K, 4K Supported MIME types: image/png, image/jpeg, image/webp, image/heic, image/heif
	Text	Maximum number of files per prompt: As supported by the 128k token context window Maximum number of pages per file: As supported by the 128k token context window Maximum file size per file: 50 MB (API and Cloud Storage imports) or 7 MB (direct upload through Google Cloud console) Supported MIME types: application/pdf, text/plain
	Video	Maximum number of input video files per prompt: 10 Maximum YouTube URLs per prompt: 1 Maximum video length (without audio): As supported by the 128k token context window (approximately 25 minutes). Supported MIME types: video/x-flv, video/quicktime, video/mpeg, video/mpegs, video/mpg, video/mp4, video/webm, video/wmv, video/3gpp
	Parameter defaults	candidateCount: 1 Temperature, topP, topK, seed, logprobs: Not supported
Supported regions	Model availability	Global: global
	Provisioned Throughput	Global: global
	Standard PayGo	Global: global
Versions	gemini-nano-banana-2.1 Launch stage: GA Release date: October 6, 2026
Security controls	Online prediction	Data residency CMEK VPC-SC AXT
	Batch inference	Data residency CMEK VPC-SC AXT
	Context caching	Data residency CMEK VPC-SC AXT
	See Security controls for more information.

Image generation specifications

Nano Banana 2.1 consumes 1,120 tokens per input image.

Output image token consumption varies based on the generated image resolution:

Output resolution	Approximate megapixels	Output image tokens
1K	1	1,120
2K	4	1,680
4K	16	3,780

Note: Additional charges apply for input and output tokens for other modalities, such as text and video. Refer to the pricing page for the latest.

For more information about image generation using Nano Banana 2.1, see Generate and edit images with Gemini.