Skip to main content
Gemini 2.5 Flash Lite is the lightest and most efficient language model in Google’s 2.5 series, available through Starrise AI via the native Gemini API. Ideal for large-scale scenarios that are sensitive to response speed and cost.

​
Key Capabilities

  • Native Gemini API — Uses Google’s native API format for full feature access
  • Ultra-efficient — Lowest latency and lowest cost in the Gemini 2.5 series
  • Multi-turn conversation — Conversations with system instructions
  • High throughput — Suitable for large-scale, cost-sensitive workloads

​
Quick Example

curl "https://ai.alad.com/v1beta/models/gemini-2.5-flash-lite: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 2.5 Flash Lite.