Gemini 3 Flash Preview API Guide: Google's Fast & Affordable AI Model

from openai import OpenAI

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

# Basic text generation
response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a FastAPI endpoint for user registration with email validation."}
    ],
    max_tokens=2048,
    temperature=0.7
)

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

import base64

# Analyze an image
with open("architecture_diagram.png", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Analyze this system architecture diagram. Identify potential bottlenecks and suggest improvements."},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{image_b64}"}
                }
            ]
        }
    ],
    max_tokens=2048
)

# Process a massive codebase (up to 1M tokens)
import os

def read_codebase(directory: str) -> str:
    """Read all source files from a directory."""
    code = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith(('.py', '.js', '.ts', '.go', '.rs')):
                filepath = os.path.join(root, file)
                with open(filepath) as f:
                    code.append(f"### {filepath}\n```\n{f.read()}\n```\n")
    return "\n".join(code)

codebase = read_codebase("./my-project/src")

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "system", "content": "You are a senior software architect."},
        {"role": "user", "content": f"Review this entire codebase and provide:\n1. Architecture overview\n2. Code quality issues\n3. Security vulnerabilities\n4. Performance improvements\n\n{codebase}"}
    ],
    max_tokens=8192
)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your-crazyrouter-api-key',
  baseURL: 'https://api.crazyrouter.com/v1',
});

// Streaming response for real-time UI
const stream = await client.chat.completions.create({
  model: 'gemini-3-flash-preview',
  messages: [
    { role: 'user', content: 'Explain microservices architecture patterns with examples.' },
  ],
  max_tokens: 4096,
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

curl https://api.crazyrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-crazyrouter-api-key" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [
      {"role": "user", "content": "Compare PostgreSQL and MongoDB for a real-time analytics platform."}
    ],
    "max_tokens": 2048
  }'

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["location"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search_flights",
            "description": "Search for flights between two cities",
            "parameters": {
                "type": "object",
                "properties": {
                    "origin": {"type": "string"},
                    "destination": {"type": "string"},
                    "date": {"type": "string", "description": "YYYY-MM-DD format"}
                },
                "required": ["origin", "destination", "date"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "user", "content": "I want to fly from Tokyo to New York next Friday. What's the weather like there?"}
    ],
    tools=tools,
    tool_choice="auto"
)

# Gemini 3 Flash handles parallel tool calls efficiently
for tool_call in response.choices[0].message.tool_calls:
    print(f"Call: {tool_call.function.name}({tool_call.function.arguments})")

# System prompts and common context get cached automatically
# after the first request, reducing costs by ~75%
response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {
            "role": "system",
            "content": long_system_prompt  # Cached after first call
        },
        {"role": "user", "content": user_query}
    ]
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "user", "content": "Extract all entities from this text: 'Apple CEO Tim Cook announced the new iPhone 17 at WWDC 2026 in San Jose.'"}
    ],
    response_format={"type": "json_object"}
)