Skip to main content
Gemini 3.1 Flash Lite Preview is Google’s lightweight and efficient language model, available through Starrise AI via the native Gemini API. Optimized for low latency and cost efficiency, suitable for high-throughput applications.

​
Key Capabilities

  • Native Gemini API — Uses Google’s native API format for full feature access
  • Fast inference — Optimized for low-latency responses
  • Multi-turn conversation — Complex conversations with system instructions
  • Cost-efficient — Suitable for large-scale, high-concurrency applications

​
Quick Example

curl "https://ai.alad.com/v1beta/models/gemini-3.1-flash-lite-preview:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{ "text": "Explain quantum computing in simple terms." }]
      }
    ],
    "generationConfig": {
      "temperature": 1,
      "topP": 1
    }
  }'

​
Parameters

ParameterTypeRequiredDescription
keystringYesAPI key (query parameter)
contentsarrayYesArray of { role, parts } objects
systemInstructionobjectNoSystem instruction with parts array
generationConfig.temperaturefloatNo0–2, controls randomness, default 1
generationConfig.topPfloatNoNucleus sampling threshold, default 1

API Reference

View the interactive API Playground for Gemini 3.1 Flash Lite Preview.