Gemini 3.1 Flash Lite Preview: Google's Latest Lightweight Model for Agent Tasks & Low Latency

import openai

# Configure APIYi client
client = openai.OpenAI(
    api_key="your-apiyi-api-key",  # Replace with your APIYi API key
    base_url="https://api.apiyi.com/v1"
)

# Call Gemini 3.1 Flash Lite Preview
response = client.chat.completions.create(
    model="gemini-3.1-flash-lite-preview",
    messages=[
        {
            "role": "system",
            "content": "You are an efficient data extraction assistant. Extract structured information from user-provided text."
        },
        {
            "role": "user",
            "content": "Extract the company name, founding year, and main business from: APIYi was founded in 2024, a tech company focused on AI model API proxy services, supporting 400+ popular AI models."
        }
    ],
    max_tokens=1024,
    temperature=0.3,
    response_format={"type": "json_object"}
)

print(response.choices[0].message.content)

import openai
import json

client = openai.OpenAI(
    api_key="your-apiyi-api-key",
    base_url="https://api.apiyi.com/v1"
)

# Define tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather information for a specified city",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "City name"}
                },
                "required": ["city"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="gemini-3.1-flash-lite-preview",
    messages=[{"role": "user", "content": "What's the weather like in Beijing today?"}],
    tools=tools,
    tool_choice="auto"
)

print(response.choices[0].message.tool_calls)