🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
G

Gemini 3.1 Flash Lite Image

GoogleModel IDgemini-3.1-flash-lite-image
G

Gemini 3.1 Flash Lite Image

GoogleModel IDgemini-3.1-flash-lite-image

Gemini 3.1 Flash Lite Image, also known as Nano Banana 2 Lite, is Google's ultra-low-latency and cost-efficient image generation and editing model. It supports text, image, video, and PDF inputs, fast conversational image editing, multimodal reasoning, up to 14 reference images, and native 1K image generation.

ModeText / Image / File / Video → Text / Image
Input price$0.25 / 1M tokens
Output price$30 / 1M tokens
Context length65536 tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Google
Input modality
Text / Image / File / Video
Output modality
Text / Image
Max output
4096 tokens

Pricing

ProviderBilling typePrice summary
G
Gemini-Balanced
Per token
Input price$0.25per 1M tokens
Completion price$30per 1M tokens
Cache read price—
Cache write price—
G
Gemini-Custom
Per token
Input price$0.25per 1M tokens
Completion price$30per 1M tokens
Cache read price—
Cache write price—

Integration

Code Example

curl http://127.0.0.1:4179/v1/models/gemini-3.1-flash-lite-image:generateContent \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-lite-image",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
google-generate-content

Supported Parameters

ParameterTypeDefaultDescription
string1024pxOutput image size. Gemini 3.1 Flash Lite Image supports 1K (1024px) output only.
string1:1Controls the aspect ratio of the generated image.
stringminimalControls reasoning depth. Supported values: minimal and high.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.