Nano Banana 2 API guide

Use case

Image teams evaluating Gemini image routes need the public model alias, endpoint, resolution parameters, and per-image pricing assumptions in one place.

Available models and pricing

The Nano Banana family is present in the pricing catalog. Start with nano-banana-2 for new integrations, then compare related models by output quality, cost, and reference-image needs.

• nano-banana-2: $0.0369/image after 0.55x discount; public_endpoint_types = image-generation.
• nano-banana-pro: $0.0737/image after 0.55x discount; public_endpoint_types = image-generation.
• nano-banana: $0.0215/image after 0.55x discount; public_endpoint_types = image-generation.

Request fields

Use POST /v1/images/generations with model nano-banana-2. The public parameters are prompt, image_input, resolution, aspect_ratio, output_format, output_compression, and n. Do not pass Gemini-native fields such as generationConfig or imageOutputOptions.

• Text-to-image: omit image_input.
• Reference image edit: pass one or more image URLs in image_input.
• Use output_format png, jpeg, or jpg depending on downstream needs.

Implementation checklist

Begin with one 1K image and one reference-free prompt. Add image_input, aspect_ratio, resolution, and output format controls only after the baseline request is stable.

cn.crazyrouter.com test evidence

Only checks that returned 200 are shown here. API requests use https://cn.crazyrouter.com; account, billing, and console actions use https://crazyrouter.com.

Implementation examples

curl -X POST https://cn.crazyrouter.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "nano-banana-2",
    "prompt": "A clean ecommerce hero shot of a red apple on a white background",
    "n": 1
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://cn.crazyrouter.com/v1",
)

response = client.images.generate(
    model="nano-banana-2",
    prompt="A clean ecommerce hero shot of a red apple on a white background",
    n=1,
)

print(response.data[0].url)

FAQ