Google (Gemini)

Overview

Google AI provides the Gemini series of multimodal models with long context windows and native multimodal understanding.

Official Website: https://ai.google.dev API Documentation: https://ai.google.dev/docs

Key Features

• Long Context — Very large context windows
• Native Multimodal — Built-in vision, audio, video understanding
• Deep Thinking — Extended reasoning capabilities
• Grounding — Connect to real-time information
• Code Execution — Built-in code execution

Usage Example

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="model-id",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

Available Models

Use the Models API to query available models:

curl https://api.yuhuanstudio.com/v1/models?provider=google \
  -H "Authorization: Bearer YOUR_API_KEY"

Official Resources

• Google AI Studio
• API Documentation
• Pricing