NanoBanana Pro

NanoBanana Pro is Gemini’s image generation service. It supports multiple aspect ratios (1:1, 16:9, 9:16, etc.) and resolutions (1K, 2K, 4K). All resolutions share the same price; 4K is slower to generate and not recommended. See Pricing.

Endpoint: POST https://aiberm.com/v1beta/models/gemini-3-pro-image-preview:generateContent

Key points: Send the image description in request body contents; set responseModalities, imageConfig (aspect ratio, resolution) in generationConfig. The generated image is in candidates[0].content.parts as inline_data.

Example code

Python uses snake_case (e.g. response_modalities); REST/cURL uses camelCase (e.g. responseModalities). They mean the same.

1from google import genai
2from google.genai import types
3 
4base_url = "https://aiberm.com"
5api_key = "YOUR_API_KEY"
6prompt = "Generate a cute sea otter image"
7model = "gemini-3-pro-image-preview"
8output_file = "gemini_sdk_generated.png"
9 
10# Image generation config
11response_modalities = ["IMAGE"]  # or ["TEXT", "IMAGE"]
12aspect_ratio = "16:9"  # "1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"
13image_size = "2K"  # "1K", "2K", "4K" (gemini-3-pro-image-preview only)
14 
15# Generation params
16temperature = 1.0
17top_p = 0.95
18max_output_tokens = 8192
19enable_google_search = False  # Enable Google Search(adds latency & cost; disable for image-only)
20 
21client = genai.Client(
22  api_key=api_key,
23  http_options=types.HttpOptions(api_version="v1beta", base_url=base_url)
24)
25 
26config = types.GenerateContentConfig(
27  response_modalities=response_modalities,
28  temperature=temperature,
29  top_p=top_p,
30  max_output_tokens=max_output_tokens,
31  system_instruction="You are a helpful assistant.",
32  image_config=types.ImageConfig(
33      aspect_ratio=aspect_ratio,
34      image_size=image_size if "pro-image" in model else None
35  )
36)
37if enable_google_search:
38  config.tools = [{"google_search": {}}]
39 
40response = client.models.generate_content(
41  model=model,
42  contents=[prompt],
43  config=config
44)
45 
46for part in response.parts:
47  if part.text is not None:
48      print(part.text)
49  elif part.inline_data is not None:
50      part.as_image().save(output_file)
51      print(f"Image saved: {output_file}")

cURL image parameters

Below are parameter names (camelCase) for cURL; use snake_case in Python (e.g. aspectRatio → aspect_ratio).

imageConfig (generationConfig.imageConfig or SDK ImageConfig):

aspectRatio string — 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
imageSize string — 1K, 2K, 4K (gemini-3-pro-image-preview only)

Other common generationConfig fields:

responseModalities string[] — ["IMAGE"] or ["TEXT", "IMAGE"]
temperature number — 0–2, higher = more random
topP number — 0–1, diversity
maxOutputTokens number — e.g. 8192
systemInstruction object — e.g. {"parts": [{"text": "..."}]}
tools array — e.g. [{"google_search": {}}]

Enabling Google Search

Only the Gemini-style API supports Google Search. Pass tools in the config; the model will use real-time web info when needed.

Not recommended by default: Adds latency and cost; unnecessary for image-only use. Turn off if you don’t need search.

Python (SDK):

config = types.GenerateContentConfig(
    # ... other params like response_modalities, image_config
    tools=[{"google_search": {}}]
)
response = client.models.generate_content(model=model, contents=[prompt], config=config)

cURL (REST):

Add tools at the top level of the request body:

curl -X POST "https://aiberm.com/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Your question"}]}],
    "generationConfig": { ... },
    "tools": [{"google_search": {}}]
  }'

FAQ

No image in response: Ensure model is gemini-3-pro-image-preview and the prompt is a clear image description.
Decode error: Use only the base64 string after data:image/...;base64, and remove newlines before decoding.