API docs / Image models
Nano Banana API
Generates and edits images based on text prompts and optional input images. Maintains character and style consistency across multiple generations, enabling users to place the same character or object in different environments without fine-tuning. Supports multi-image fusion to blend multiple input images into cohesive visuals. Performs conversational editing tasks like background blurring, object removal, pose alteration, and colorization through natural language descriptions. Leverages Gemini's world knowledge for visual reasoning tasks including interpreting hand-drawn diagrams and following complex multi-step instructions. Features native image understanding as part of its core architecture, allowing seamless workflows between image creation and editing. Demonstrates fast generation speed, producing images 2-3 times faster than comparable models while maintaining quality. Includes SynthID watermarking technology to identify AI-generated content.
- Model id
google/nano-banana- Provider
- Output
- Image
- Price
- From 14 credits per run, the same as on voor.ai. Options such as length or resolution can change it.
Request
POST https://voor.ai/v1/generations with "model": "google/nano-banana". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.
curl https://voor.ai/v1/generations \
-H "Authorization: Bearer $VOOR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "google/nano-banana",
"input": {
"prompt": "A red fox standing in fresh snow at golden hour, soft light"
},
"callback_url": "https://example.com/webhooks/voor"
}'
# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
-H "Authorization: Bearer $VOOR_API_KEY"Input parameters
| Name | Type | Details |
|---|---|---|
promptrequired | string | A text description of the image you want to generate |
reference_images | array of URLs | Input images to transform or use as reference (supports multiple images) Default: Up to 10 files · Accepts image/* |
aspect_ratio | string | Default: One of: match_input_image, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
output_format | string | Default: One of: jpg, png |