Google modelsimage generation api

google/nano-banana-pro

Name: Nano Banana Pro
Author: Google

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

Input

Prompt(string)

The text prompt to generate an image from.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Resolution(string)

The resolution of the image to generate. Allowed values: 1K, 2K, 4K.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDgoogle/nano-banana-pro

Input Schema

4 parameters · 1 required · 3 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The text prompt to generate an image from. · Min length: 3 · Max length: 50000 · Default: "a cat sitting on a windowsill, golden hour lighting, photorealistic"
`resolution`	string	Optional	The resolution of the image to generate. · Options: 1K, 2K, 4K · Default: "1K" 1K2K4K
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 · Default: "1:1" 21:916:93:24:35:41:14:53:42:39:16
`output_format`	string	Optional	The format of the generated image. · Options: jpeg, png · Default: "png" jpegpng

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "google/nano-banana-pro",
  "prompt": "a cat sitting on a windowsill, golden hour lighting, photorealistic",
  "resolution": "1K",
  "aspect_ratio": "1:1",
  "output_format": "png"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Nano Banana Pro

API README

Google Nano Banana Pro Text-to-Image

Google's latest image generation model built on Gemini architecture. Delivers high-quality images with strong prompt understanding, native multilingual text rendering, and flexible aspect ratios — at a fraction of the cost of competing models.

Need to edit an existing image? Try Nano Banana Pro Edit.

Highlights

Native text rendering — Generates readable text in images across Latin, Chinese, Japanese, and Korean scripts. Handles signage, labels, posters, and UI elements with correct spelling and natural placement.

Strong prompt adherence — Follows complex multi-part prompts faithfully. Composition, lighting, color palette, and fine details described in long prompts are preserved without drift or hallucination.

Flexible resolution — Supports 1K, 2K, and 4K output resolutions with multiple aspect ratios from ultra-wide 21:9 to portrait 9:16.

Cost-efficient — $0.12 per generation (1K/2K), $0.24 for 4K output. Competitive pricing for high-volume workflows.

Pricing

Resolution	Price
1K	$0.12
2K	$0.12
4K	$0.24

When to Use

✅ Good fit	❌ Consider alternatives
Blog covers and marketing images	Pixel-perfect brand assets (use GPT Image 2)
Social media content	Iterative mask-based editing (use Edit model)
Text-heavy posters and ads	Video or animation
Concept art and brainstorming	Sub-second generation
Multilingual visual content	Ultra-high resolution print (4K+)

Prompt Guide

Structure your prompts for best results:

Scene: [environment, time of day, background]
Subject: [main focus, position, action]
Details: [materials, lighting, camera angle, mood]
Text: [exact text to render, font style, placement]
Style: [photorealistic, illustration, flat design, etc.]

Example:

Create a 16:9 blog hero image for a tech article. A clean, modern workspace with a laptop showing code on screen, warm afternoon lighting from a window on the left. Title text "Build Faster with AI" in bold sans-serif at the top. Minimalist style, muted blue and white palette.

Technical Specs

Spec	Value
Input	Text prompt (max 50,000 characters)
Output	PNG or JPEG
Resolution	1K / 2K / 4K
Aspect ratio	21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
Execution	Async (submit → poll for result)
Typical latency	20–40 seconds

Nano Banana Pro Edit — Edit existing images with multi-image reference support