import requests import os from typing import Optional # Configuration UNOROUTER_BASE_URL = "https://api.unorouter.com/v1" MODEL = "google/gemini-3.6-flash:free" class GeminiClient: """Client for interacting with Gemini 3.6 Flash via Unorouter.""" def __init__(self, api_key: Optional[str] = None): self.api_key = api_key or os.getenv("UNOROUTER_API_KEY") if not self.api_key: raise ValueError("API key required. Set UNOROUTER_API_KEY environment variable.") self.headers = { "Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json" } self.url = f"{UNOROUTER_BASE_URL}/chat/completions" def generate(self, prompt: str, temperature: float = 0.7, max_tokens: int = 1000, system_prompt: Optional[str] = None) -> str: """Generate text completion.""" messages = [] if system_prompt: messages.append({"role": "system", "content": system_prompt}) messages.append({"role": "user", "content": prompt}) data = { "model": MODEL, "messages": messages, "temperature": temperature, "max_tokens": max_tokens } response = requests.post(self.url, headers=self.headers, json=data, timeout=30) response.raise_for_status() return response.json()["choices"][0]["message"]["content"] # Usage Example if __name__ == "__main__": client = GeminiClient() # Simple text generation  prompt = "Write a Python function to calculate fibonacci numbers" result = client.generate(prompt) print(f"Prompt: {prompt}") print(f"Response:\n{result}") 

import json def stream_generate(self, prompt: str, system_prompt: Optional[str] = None): """Stream text generation for real-time display.""" messages = [] if system_prompt: messages.append({"role": "system", "content": system_prompt}) messages.append({"role": "user", "content": prompt}) data = { "model": MODEL, "messages": messages, "temperature": 0.7, "max_tokens": 1000, "stream": True } response = requests.post( self.url, headers=self.headers, json=data, timeout=30, stream=True ) response.raise_for_status() for line in response.iter_lines(): if line: line = line.decode('utf-8') if line.startswith('data: '): line = line[6:] if line.strip() == '[DONE]': break try: chunk = json.loads(line) content = chunk["choices"][0]["delta"].get("content", "") if content: print(content, end="", flush=True) except: pass print() # Add to class GeminiClient.stream = stream_generate # Usage client.stream("Write a short story about a robot learning to paint") 

class ChatSession: """Maintains conversation context across multiple turns.""" def __init__(self, client: GeminiClient, system_prompt: Optional[str] = None): self.client = client self.messages = [] if system_prompt: self.messages.append({"role": "system", "content": system_prompt}) def send(self, user_message: str) -> str: self.messages.append({"role": "user", "content": user_message}) data = { "model": MODEL, "messages": self.messages, "temperature": 0.7, "max_tokens": 1000 } response = requests.post(self.client.url, headers=self.client.headers, json=data, timeout=30) response.raise_for_status() reply = response.json()["choices"][0]["message"]["content"] self.messages.append({"role": "assistant", "content": reply}) return reply def get_history(self) -> list: return self.messages # Usage client = GeminiClient() chat = ChatSession(client, "You are a helpful Python tutor.") print(chat.send("How do I read a JSON file in Python?")) print(chat.send("Can you show me with error handling?")) print(chat.send("What about writing JSON files?")) 

import time from functools import wraps def retry_on_rate_limit(max_retries: int = 3, base_delay: float = 2.0): """Decorator for handling rate limits with exponential backoff.""" def decorator(func): @wraps(func) def wrapper(*args, **kwargs): for attempt in range(max_retries): try: return func(*args, **kwargs) except requests.exceptions.HTTPError as e: if e.response.status_code in (429, 503): delay = base_delay ** attempt print(f"Rate limited. Waiting {delay}s... (attempt {attempt + 1}/{max_retries})") time.sleep(delay) else: raise raise Exception(f"Max retries ({max_retries}) exceeded") return wrapper return decorator # Apply to generate method @retry_on_rate_limit(max_retries=3) def robust_generate(self, prompt: str, **kwargs) -> str: return self.generate(prompt, **kwargs) GeminiClient.robust_generate = robust_generate 

#!/usr/bin/env python3 """ Complete Gemini 3.6 Flash Demo via Unorouter Run: python gemini_demo.py """ import os import requests import json import time from typing import Optional # ============== CONFIGURATION ============== UNOROUTER_BASE_URL = "https://api.unorouter.com/v1" MODEL = "google/gemini-3.6-flash:free" API_KEY = os.getenv("UNOROUTER_API_KEY") if not API_KEY: print("ERROR: Please set UNOROUTER_API_KEY environment variable") print("Get your free key at: https://unorouter.com") exit(1) # ============== CLIENT CLASS ============== class GeminiClient: def __init__(self, api_key: str): self.api_key = api_key self.headers = { "Authorization": f"Bearer {api_key}", "Content-Type": "application/json" } self.url = f"{UNOROUTER_BASE_URL}/chat/completions" def generate(self, prompt: str, temperature: float = 0.7, max_tokens: int = 1000) -> str: data = { "model": MODEL, "messages": [{"role": "user", "content": prompt}], "temperature": temperature, "max_tokens": max_tokens } response = requests.post(self.url, headers=self.headers, json=data, timeout=30) response.raise_for_status() return response.json()["choices"][0]["message"]["content"] def stream(self, prompt: str): data = { "model": MODEL, "messages": [{"role": "user", "content": prompt}], "temperature": 0.7, "max_tokens": 1000, "stream": True } response = requests.post(self.url, headers=self.headers, json=data, timeout=30, stream=True) response.raise_for_status() for line in response.iter_lines(): if line: line = line.decode('utf-8') if line.startswith('data: '): line = line[6:] if line.strip() == '[DONE]': break try: chunk = json.loads(line) content = chunk["choices"][0]["delta"].get("content", "") if content: print(content, end="", flush=True) except: pass print() # ============== DEMO FUNCTIONS ============== def demo_basic_generation(client: GeminiClient): print("=" * 60) print("DEMO 1: Basic Text Generation") print("=" * 60) prompt = "Explain decorators in Python in 3 sentences" print(f"Prompt: {prompt}\n") result = client.generate(prompt) print(f"Response:\n{result}\n") def demo_streaming(client: GeminiClient): print("=" * 60) print("DEMO 2: Streaming Response") print("=" * 60) prompt = "Write a haiku about coding" print(f"Prompt: {prompt}\nResponse: ") client.stream(prompt) print() def demo_code_generation(client: GeminiClient): print("=" * 60) print("DEMO 3: Code Generation") print("=" * 60) prompt = """Write a complete Python class for a simple REST API client with: - GET, POST, PUT, DELETE methods - Automatic JSON handling - Error handling with retries - Type hints""" print(f"Prompt: {prompt}\n") result = client.generate(prompt, temperature=0.5, max_tokens=1500) print(f"Response:\n{result}\n") def demo_creative_writing(client: GeminiClient): print("=" * 60) print("DEMO 4: Creative Writing") print("=" * 60) prompt = "Write a micro-fiction story (100 words) about an AI that discovers it can dream" print(f"Prompt: {prompt}\n") result = client.generate(prompt, temperature=0.9, max_tokens=500) print(f"Response:\n{result}\n") # ============== MAIN ============== if __name__ == "__main__": print("Gemini 3.6 Flash via Unorouter - Complete Demo") print("=" * 60) client = GeminiClient(API_KEY) demo_basic_generation(client) demo_streaming(client) demo_code_generation(client) demo_creative_writing(client) print("=" * 60) print("All demos completed successfully!") print("=" * 60)