Gemini 3.1 Flash Lite Image

Gemini 3.1 Flash Lite Image is Google’s low-latency, cost-effective image generation and editing model, available through AnyFast via the native Gemini API. It is also known as Nano Banana Lite and is designed for high-volume interactive image use cases.

Google lists gemini-3.1-flash-lite-image as the stable model ID for Nano Banana Lite. The official model page shows a June 2026 latest update and describes the model as optimized for sub-2 second latency, lower TPU compute cost, and high-volume image generation and editing.

Key capabilities

Text-to-image — Generate images from text descriptions
Image editing — Pass a reference image in inline_data alongside your text instruction
Low latency — Targeted for sub-2 second end-to-end latency
Aspect ratio control — 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
Resolution control — Supports 1K (1024px). 2K and 4K are not supported.
Thinking control — Supports minimal and high thinking levels
Multi-modal output — Return both the image and a text caption with responseModalities: ["TEXT", "IMAGE"]
Watermarking — SynthID is always on, with C2PA watermarking

Note: If you need the generated image returned as a URL, select the Aggregate-NanoUrl group when creating your API token.

Text-to-image example

curl "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          { "text": "Generate an image of a sunset over mountains" }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "1K"
      }
    }
  }'

import requests, base64

url = "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent"
response = requests.post(url, params={"key": "YOUR_API_KEY"}, json={
    "contents": [
        {
            "role": "user",
            "parts": [{"text": "Generate an image of a sunset over mountains"}]
        }
    ],
    "generationConfig": {
        "responseModalities": ["TEXT", "IMAGE"],
        "imageConfig": {"aspectRatio": "16:9", "imageSize": "1K"}
    }
})

for part in response.json()["candidates"][0]["content"]["parts"]:
    image_part = part.get("inlineData")
    if image_part:
        with open("output.jpg", "wb") as f:
            f.write(base64.b64decode(image_part["data"]))
        print("Image saved to output.jpg")
    elif "text" in part:
        print("Caption:", part["text"])

import google.genai as genai

client = genai.Client(api_key="YOUR_API_KEY")

response = client.models.generate_content(
    model="gemini-3.1-flash-lite-image",
    contents="Generate an image of a sunset over mountains",
    config={
        "responseModalities": ["TEXT", "IMAGE"],
        "imageConfig": {
            "aspectRatio": "16:9",
            "imageSize": "1K"
        }
    }
)

for candidate in response.candidates:
    for part in candidate.content.parts:
        if part.inline_data:
            with open("output.jpg", "wb") as f:
                f.write(part.inline_data.data)
            print("Image saved to output.jpg")
        elif part.text:
            print("Caption:", part.text)

Image editing example (with reference image)

Include both a text instruction and an inline_data reference image in the same parts array.

# First encode your image to base64:
# BASE64=$(base64 -i your_photo.jpg)
#
# Then send the request:
curl "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "Hi, this is a picture of me. Can you add a llama next to me?"
          },
          {
            "inline_data": {
              "mime_type": "image/jpeg",
              "data": "<YOUR_BASE64_ENCODED_IMAGE>"
            }
          }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {
        "aspectRatio": "1:1",
        "imageSize": "1K"
      }
    }
  }'

import requests, base64

# Read and encode your reference image
with open("your_photo.jpg", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode("utf-8")

url = "https://www.anyfast.ai/v1beta/models/gemini-3.1-flash-lite-image:generateContent"
response = requests.post(url, params={"key": "YOUR_API_KEY"}, json={
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Hi, this is a picture of me. Can you add a llama next to me?"
                },
                {
                    "inline_data": {
                        "mime_type": "image/jpeg",
                        "data": image_b64          # ← paste your base64 string here
                    }
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": ["TEXT", "IMAGE"],
        "imageConfig": {"aspectRatio": "1:1", "imageSize": "1K"}
    }
})

for part in response.json()["candidates"][0]["content"]["parts"]:
    image_part = part.get("inlineData")
    if image_part:
        with open("output.jpg", "wb") as f:
            f.write(base64.b64decode(image_part["data"]))
        print("Image saved to output.jpg")
    elif "text" in part:
        print("Caption:", part["text"])

import google.genai as genai

client = genai.Client(api_key="YOUR_API_KEY")

# Read and encode your reference image
with open("your_photo.jpg", "rb") as f:
    image_bytes = f.read()

response = client.models.generate_content(
    model="gemini-3.1-flash-lite-image",
    contents=[
        "Hi, this is a picture of me. Can you add a llama next to me?",
        genai.types.Part.from_bytes(data=image_bytes, mime_type="image/jpeg")
    ],
    config={
        "responseModalities": ["TEXT", "IMAGE"],
        "imageConfig": {
            "aspectRatio": "1:1",
            "imageSize": "1K"
        }
    }
)

for candidate in response.candidates:
    for part in candidate.content.parts:
        if part.inline_data:
            with open("output.jpg", "wb") as f:
                f.write(part.inline_data.data)
            print("Image saved to output.jpg")
        elif part.text:
            print("Caption:", part.text)

Parameters

Parameter	Type	Required	Description
`key`	string	Yes	API key (query parameter)
`contents[].parts[].text`	string	Yes	Text prompt or instruction
`contents[].parts[].inline_data.mime_type`	string	No	Reference image type: `image/jpeg`, `image/png`, `image/webp`
`contents[].parts[].inline_data.data`	string	No	Base64-encoded reference image
`generationConfig.responseModalities`	array	Yes	`["IMAGE"]` or `["TEXT", "IMAGE"]`
`generationConfig.imageConfig.aspectRatio`	string	No	`1:1` / `3:2` / `2:3` / `3:4` / `4:3` / `4:5` / `5:4` / `9:16` / `16:9` / `21:9`
`generationConfig.imageConfig.imageSize`	string	No	`1K` only. 2K and 4K are not supported.

API Reference

View the interactive API playground for Gemini 3.1 Flash Lite Image.

Getting started

Model Introduction

Resources

Gemini 3.1 Flash Lite Image

Key capabilities

Text-to-image example

Image editing example (with reference image)

Parameters

API Reference

​Key capabilities

​Text-to-image example

​Image editing example (with reference image)

​Parameters

API Reference

Key capabilities

Text-to-image example

Image editing example (with reference image)

Parameters