About Nano Banana 2 Lite
Nano Banana 2 Lite is Google's fastest and most cost-efficient Gemini image model. It generates or edits images from text prompts with sub-2 second latency, making it suited to high-volume pipelines, rapid iteration, and real-time applications where speed and cost matter more than 2K or 4K output.
The model supports text-to-image generation, single-reference editing, and fast local edits such as color swaps or background changes. It outputs at 1K resolution across 14 aspect ratios. It is not optimized for heavy multi-reference composition or long multi-turn editing sessions; use Nano Banana 2 or Nano Banana Pro for those workflows.
| Metric | Value |
|---|---|
| Context Length | 65,536 tokens |
Ready to build with Nano Banana 2 Lite?
Try Nano Banana 2 Lite in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "nano-banana-2-lite",
"prompt": "A cat sitting on a chair",
"aspect_ratio": "16:9",
"resolution": "1K",
"thinking_level": "minimal"
}'Request parameters
Every field Nano Banana 2 Lite accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/edit| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text description of what you want to generate, or the instruction on how to edit the given image. Use @Image1, @Image2, etc. to reference the input images. |
input_image | array<string>nullable | No | — | Optional reference image to edit. Leave empty to generate from the prompt alone. Reference it in the prompt as @Image1. |
aspect_ratio | string | No | "16:9" | auto1:116:99:164:33:43:22:34:55:421:94:11:48:11:8 |
resolution | string | No | "1K" | 1K |
thinking_level | string | No | "minimal" | How much the model reasons before generating. 'high' improves complex compositions at higher latency and cost.minimalhigh |