Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) API
Google's fastest, most cost-efficient image generation and editing model in the Nano Banana family, built for high-volume, cost-sensitive creative work.
Nano Banana 2 Lite, officially Gemini 3.1 Flash-Lite Image, is the speed-first member of Google's Nano Banana image family. It is built on Gemini 3.1 technology, positioned as a direct replacement for the first Nano Banana, and reached general availability on June 23, 2026.
It accepts text, images and video as input and returns images. It supports multi-turn image editing, generating images from video input, interleaved image and text output, virtual try-on and portrait generation, and it uses world knowledge to render landmarks, scenes and specific objects more accurately. Limits are 65,536 input tokens and 4,096 output tokens, with 1,120 tokens per input image and up to 14 images or 10 videos per prompt. Output resolution is 1K, with aspect ratios from 1:1 and 1:4 through 21:9, and inputs can be PNG, JPEG, WebP, HEIC or HEIF images and MP4, WebM or MOV video.
It fits high-throughput, cost-sensitive workflows: rapid creative ideation, A/B testing of ad variants, large-scale image generation for social apps, storyboarding tools, e-commerce virtual try-on, and real-time slide or web content. Thinking, system instructions, implicit context caching and C2PA Content Credentials are supported, while structured outputs, function calling, code execution and grounding are not. It also pairs with Gemini Omni Flash for an image-to-video pipeline.
Updated:
MODEL ID
gemini-3.1-flash-lite-image- Context
- 65.536K
- Max output
- 58.982K
- Input
- image / text
- Output
- image / text
Highlights
- Text-to-image in about 4 seconds
- Up to 14 images or 10 videos per prompt
- 1K output resolution
- Multi-turn image editing
- Video input to image output
- No function calling or grounding
Providers
Best priceCompare API prices across providers. Select a provider to view all charges and conditions.
| $0.25 | $1.5 | |
| $0.25 | $1.5 |
Reasoning
- Default effort
- minimal
- Enabled by default
- Yes
- Always enabled
- No
- Available effort levels
- high / minimal / none
API reference
Model-specific protocol details are not published. Check the API reference for integration requirements.
API reference →Supported parameters
- include_reasoning
- max_tokens
- reasoning
- reasoning_effort
- response_format
- seed
- temperature
- top_p
Frequently asked questions
What is Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)?
Nano Banana 2 Lite, officially Gemini 3.1 Flash-Lite Image, is the speed-first member of Google's Nano Banana image family. It is built on Gemini 3.1 technology, positioned as a direct replacement for the first Nano Banana, and reached general availability on June 23, 2026. It accepts text, images and video as input and returns images. It supports multi-turn image editing, generating images from video input, interleaved image and text output, virtual try-on and portrait generation, and it uses world knowledge to render landmarks, scenes and specific objects more accurately. Limits are 65,536 input tokens and 4,096 output tokens, with 1,120 tokens per input image and up to 14 images or 10 videos per prompt. Output resolution is 1K, with aspect ratios from 1:1 and 1:4 through 21:9, and inputs can be PNG, JPEG, WebP, HEIC or HEIF images and MP4, WebM or MOV video. It fits high-throughput, cost-sensitive workflows: rapid creative ideation, A/B testing of ad variants, large-scale image generation for social apps, storyboarding tools, e-commerce virtual try-on, and real-time slide or web content. Thinking, system instructions, implicit context caching and C2PA Content Credentials are supported, while structured outputs, function calling, code execution and grounding are not. It also pairs with Gemini Omni Flash for an image-to-video pipeline.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.
What inputs and outputs does Nano Banana 2 Lite support?
It accepts text, images and video as input and returns images. A single prompt can carry up to 14 images or 10 videos.
What are the token and output limits?
The input limit is 65,536 tokens and the output limit is 4,096 tokens. Each input image counts as 1,120 tokens.
What is it best suited for?
High-volume, cost-sensitive image work: rapid creative exploration, ad variant A/B testing, large-scale image generation for social apps, storyboard tools, virtual try-on and real-time slide or web content.
How does it differ from Nano Banana 2 and Nano Banana Pro?
Nano Banana 2 Lite is the speed- and cost-optimized entry in the family. Google offers Nano Banana 2 and Nano Banana Pro for users who need maximum image quality and stronger performance on complex scenes.
Does it support function calling or grounding?
No. Structured outputs, function calling, code execution and grounding are not supported. Thinking, system instructions, implicit context caching and C2PA Content Credentials are supported.
What resolutions, aspect ratios and formats are available?
Output resolution is 1K, with aspect ratios including 1:1, 1:4, 4:1, 1:8, 8:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9. Image inputs can be PNG, JPEG, WebP, HEIC or HEIF, and video inputs MP4, WebM or MOV.
Related models
Nano Banana Pro (Gemini 3 Pro Image)
GoogleImagegemini-3-pro-imageGoogle DeepMind's flagship image model built on Gemini 3 Pro, known for legible multilingual text,4K output, and studio-grade conversational editing.
Output
image / text
Context
131.072K
Input tokens
$2 / 1M tokens
Output tokens
$12 / 1M tokens
Nano Banana 2.1
GoogleImagegemini-nano-banana-2.1Google DeepMind's efficient image generation and editing model built on Gemini 3.6 Flash, with 4K output, masked local edits, and multi-reference subject consistency.
Output
image / text
Context
65.536K
Input tokens
$1.5 / 1M tokens
Output tokens
$7.5 / 1M tokens