Google Gemini 2.5 Flash image generation model. Fast and low-cost, supporting both text-to-image and image-to-image.
Pass Authorization: Bearer <YOUR_API_KEY> in the request header. Go to the API Keys management page to create and manage API Keys.
Fixed value google/nano-banana.
The prompt. Up to 6000 characters. Supports English and Chinese; detail-rich descriptions yield better results.
"An orange cat napping under a cherry blossom tree, watercolor style, soft lighting"
Reference image list. Omitting or passing an empty array means text-to-image mode; passing images switches to image-to-image / style reference mode. Up to 3 images.
3Output aspect ratio. Allowed values:
1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9
When reference images are provided and this parameter is omitted, the model automatically infers the aspect ratio from the reference images and uses it as the output ratio.
1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 Output quality tier. Currently only 1K is supported; other values will be downgraded.
1K Submitted successfully (asynchronous mode)
Unique task ID, used for subsequent polling
"task_2041350318103396352"
The model ID used for this task
"google/nano-banana"
Task creation time
"2026-04-07T03:00:17.062Z"
Unique request ID
"285f20ce-8158-401b-945c-7bc6a7ef6ead"