Multi-Model

models = {
    "premium": ["gpt-5-2025-08-07", "gpt-4.1-2025-04-14", "claude-3-5-sonnet-20241022", "gemini-1.5-pro"],
    "balanced": ["gpt-4o", "gpt-4.1-mini-2025-04-14", "claude-3-sonnet-20240229"],
    "reasoning": ["o3-2025-04-16", "o1-2024-12-17", "o3-mini-2025-01-31"]
}

models = {
    "fastest": ["gpt-5-nano-2025-08-07", "gpt-4.1-nano-2025-04-14", "claude-3-5-haiku-20241022", "gemini-1.5-flash"],
    "cost_optimised": ["gpt-5-mini-2025-08-07", "gpt-4o-mini", "claude-3-haiku-20240307"],
    "open_source": ["meta.llama3-8b-instruct-v1:0"]
}

models = {
    "maximum_context": ["gemini-1.5-pro"],  # 2M tokens
    "large_context": ["gpt-4.1-2025-04-14", "gemini-1.5-flash"],  # 1M tokens
    "standard_large": ["gpt-5-2025-08-07", "claude-3-5-sonnet-20241022", "gpt-4o"]  # 400K/200K/128K
}

models = {
    "vision": ["gpt-5-2025-08-07", "gpt-4o", "gemini-1.5-pro", "o3-2025-04-16"],
    "video": ["gemini-1.5-pro", "gemini-1.5-flash"],
    "images": ["gpt-5-2025-08-07", "gpt-4o", "o4-mini-2025-04-16", "gemini-1.0-pro-vision"]
}

from openai import OpenAI
from typing import Dict, List

class ModelSelector:
    """Intelligent model selection based on requirements"""
    
    # Model capabilities and costs
    MODEL_PROFILES = {
        "gpt-5-2025-08-07": {
            "cost": "highest",
            "speed": "medium",
            "capability": "highest",
            "context": 400000
        },
        "gpt-5-mini-2025-08-07": {
            "cost": "medium",
            "speed": "fast",
            "capability": "highest",
            "context": 400000
        },
        "gpt-5-nano-2025-08-07": {
            "cost": "low",
            "speed": "fastest",
            "capability": "good",
            "context": 400000
        },
        "gpt-4.1-2025-04-14": {
            "cost": "high",
            "speed": "medium",
            "capability": "highest",
            "context": 1047576
        },
        "gpt-4o": {
            "cost": "high",
            "speed": "medium",
            "capability": "highest",
            "context": 128000
        },
        "gpt-4o-mini": {
            "cost": "low",
            "speed": "fast",
            "capability": "good",
            "context": 128000
        },
        "o3-2025-04-16": {
            "cost": "highest",
            "speed": "slow",
            "capability": "highest",
            "context": 200000
        },
        "claude-3-5-sonnet-20241022": {
            "cost": "medium",
            "speed": "fast",
            "capability": "highest",
            "context": 200000
        },
        "claude-3-5-haiku-20241022": {
            "cost": "very_low",
            "speed": "fastest",
            "capability": "good",
            "context": 200000
        },
        "gemini-1.5-pro": {
            "cost": "medium",
            "speed": "medium",
            "capability": "highest",
            "context": 2000000
        },
        "gemini-1.5-flash": {
            "cost": "low",
            "speed": "fast",
            "capability": "good",
            "context": 1000000
        }
    }
    
    def select_model(self, 
                     task_complexity: str,
                     context_size: int,
                     budget: str,
                     speed_requirement: str) -> str:
        """Select optimal model based on requirements"""
        
        suitable_models = []
        
        for model, profile in self.MODEL_PROFILES.items():
            # Check context size
            if context_size > profile["context"]:
                continue
                
            # Check budget constraints
            if budget == "low" and profile["cost"] in ["high", "medium"]:
                continue
                
            # Check speed requirements
            if speed_requirement == "real-time" and profile["speed"] == "slow":
                continue
                
            # Check capability requirements
            if task_complexity == "complex" and profile["capability"] != "highest":
                continue
                
            suitable_models.append(model)
        
        # Return best match or default
        return suitable_models[0] if suitable_models else "gpt-4o-mini"

# Usage example
selector = ModelSelector()

# Select model for different scenarios
model_for_chat = selector.select_model(
    task_complexity="simple",
    context_size=1000,
    budget="low",
    speed_requirement="real-time"
)  # Returns: gpt-4o-mini or claude-3-5-haiku-20241022

model_for_analysis = selector.select_model(
    task_complexity="complex",
    context_size=150000,
    budget="high",
    speed_requirement="normal"
)  # Returns: claude-3-5-sonnet-20241022 or gemini-1.5-pro

import json
from typing import Dict, Optional
from openai import OpenAI

class CostOptimisedRouter:
    """Route requests to most cost-effective model"""
    
    # Cost per 1K tokens (input/output estimated)
    MODEL_COSTS = {
        "gpt-4o": {"input": 0.00250, "output": 0.01000},
        "gpt-4o-mini": {"input": 0.00015, "output": 0.00060},
        "claude-3-5-sonnet-20241022": {"input": 0.00300, "output": 0.01500},
        "claude-3-5-haiku-20241022": {"input": 0.00025, "output": 0.00125},
        "gemini-1.5-flash": {"input": 0.00010, "output": 0.00040},
        "gpt-3.5-turbo": {"input": 0.00050, "output": 0.00150}
    }
    
    def estimate_cost(self, model: str, input_tokens: int, output_tokens: int) -> float:
        """Estimate cost for a request"""
        costs = self.MODEL_COSTS.get(model, {"input": 0, "output": 0})
        input_cost = (input_tokens / 1000) * costs["input"]
        output_cost = (output_tokens / 1000) * costs["output"]
        return input_cost + output_cost
    
    def select_cheapest_capable_model(self, 
                                      task_type: str,
                                      estimated_tokens: int) -> str:
        """Select cheapest model capable of the task"""
        
        # Define capable models by task type
        capable_models = {
            "simple": ["gpt-4o-mini", "claude-3-5-haiku-20241022", "gpt-3.5-turbo"],
            "moderate": ["gpt-4o-mini", "claude-3-5-haiku-20241022", "gemini-1.5-flash"],
            "complex": ["gpt-4o", "claude-3-5-sonnet-20241022", "gemini-1.5-pro"]
        }
        
        models = capable_models.get(task_type, capable_models["simple"])
        
        # Calculate costs and select cheapest
        cheapest = min(models, key=lambda m: self.estimate_cost(
            m, estimated_tokens, estimated_tokens // 2
        ))
        
        return cheapest
    
    def route_request(self, prompt: str, complexity: str = "auto") -> Dict:
        """Route request to optimal model"""
        
        # Auto-detect complexity if needed
        if complexity == "auto":
            prompt_length = len(prompt)
            if prompt_length < 100:
                complexity = "simple"
            elif prompt_length < 500:
                complexity = "moderate"
            else:
                complexity = "complex"
        
        # Estimate tokens (rough estimate)
        estimated_tokens = len(prompt) // 4
        
        # Select model
        model = self.select_cheapest_capable_model(complexity, estimated_tokens)
        
        # Get provider for model
        provider_map = {
            "gpt-4o": "openai",
            "gpt-4o-mini": "openai",
            "gpt-3.5-turbo": "openai",
            "claude-3-5-sonnet-20241022": "anthropic",
            "claude-3-5-haiku-20241022": "anthropic",
            "gemini-1.5-pro": "google",
            "gemini-1.5-flash": "google"
        }
        
        return {
            "model": model,
            "provider": provider_map[model],
            "estimated_cost": self.estimate_cost(model, estimated_tokens, estimated_tokens // 2),
            "reasoning": f"Selected {model} as cheapest option for {complexity} task"
        }

# Usage
router = CostOptimisedRouter()

# Simple query - routes to cheapest model
result = router.route_request("What is 2+2?")
print(f"Model: {result['model']}, Cost: ${result['estimated_cost']:.6f}")

# Complex query - routes to capable but cost-effective model
result = router.route_request(
    "Analyse this 10-page legal document and identify key risks...",
    complexity="complex"
)
print(f"Model: {result['model']}, Cost: ${result['estimated_cost']:.4f}")

import asyncio
import time
from typing import List, Dict
from openai import OpenAI

class ModelABTester:
    """A/B test different models for quality and performance"""
    
    def __init__(self, gateway_url: str):
        self.gateway_url = gateway_url
        self.results = []
    
    def create_client(self, provider: str, credentials: dict) -> OpenAI:
        """Create client for specific provider"""
        headers = {"x-provider-name": provider}
        headers.update(credentials)
        
        return OpenAI(
            api_key="dummy",
            base_url=self.gateway_url,
            default_headers=headers
        )
    
    async def test_model(self, 
                         model: str, 
                         provider: str,
                         credentials: dict,
                         prompt: str) -> Dict:
        """Test a single model"""
        
        client = self.create_client(provider, credentials)
        
        start_time = time.time()
        try:
            response = client.chat.completions.create(
                model=model,
                messages=[{"role": "user", "content": prompt}],
                max_tokens=500
            )
            
            end_time = time.time()
            
            return {
                "model": model,
                "provider": provider,
                "success": True,
                "latency": end_time - start_time,
                "response": response.choices[0].message.content,
                "tokens_used": response.usage.total_tokens if response.usage else 0
            }
        except Exception as e:
            return {
                "model": model,
                "provider": provider,
                "success": False,
                "error": str(e)
            }
    
    async def run_ab_test(self, 
                         test_configs: List[Dict],
                         prompt: str) -> List[Dict]:
        """Run A/B test across multiple models"""
        
        tasks = []
        for config in test_configs:
            task = self.test_model(
                config["model"],
                config["provider"],
                config["credentials"],
                prompt
            )
            tasks.append(task)
        
        results = await asyncio.gather(*tasks)
        return results
    
    def analyse_results(self, results: List[Dict]) -> Dict:
        """Analyse A/B test results"""
        
        successful = [r for r in results if r.get("success")]
        
        if not successful:
            return {"error": "All models failed"}
        
        # Find best by latency
        fastest = min(successful, key=lambda x: x["latency"])
        
        # Calculate averages
        avg_latency = sum(r["latency"] for r in successful) / len(successful)
        
        return {
            "models_tested": len(results),
            "successful": len(successful),
            "fastest_model": fastest["model"],
            "fastest_latency": fastest["latency"],
            "average_latency": avg_latency,
            "results": results
        }

# Usage example
async def main():
    tester = ModelABTester("https://gateway.altrum.ai/v1")
    
    # Configure models to test
    test_configs = [
        {
            "model": "gpt-4o-mini",
            "provider": "openai",
            "credentials": {"Authorization": "Bearer key"}
        },
        {
            "model": "claude-3-5-haiku-20241022",
            "provider": "anthropic",
            "credentials": {"x-api-key": "key"}
        },
        {
            "model": "gemini-1.5-flash",
            "provider": "google",
            "credentials": {"x-goog-api-key": "key"}
        }
    ]
    
    # Run test
    prompt = "Write a haiku about cloud computing"
    results = await tester.run_ab_test(test_configs, prompt)
    
    # Analyse
    analysis = tester.analyse_results(results)
    print(f"Fastest model: {analysis['fastest_model']}")
    print(f"Latency: {analysis['fastest_latency']:.2f}s")

# Run the test
asyncio.run(main())

def select_model_strategy(requirements):
    """Strategic model selection based on requirements"""
    
    strategies = {
        "quality_first": [
            "gpt-5-2025-08-07",
            "gpt-4.1-2025-04-14",
            "claude-3-5-sonnet-20241022",
            "gemini-1.5-pro"
        ],
        "speed_first": [
            "gpt-5-nano-2025-08-07",
            "claude-3-5-haiku-20241022",
            "gpt-4o-mini",
            "gemini-1.5-flash"
        ],
        "cost_first": [
            "gpt-5-nano-2025-08-07",
            "gpt-4o-mini",
            "claude-3-haiku-20240307",
            "meta.llama3-8b-instruct-v1:0"
        ],
        "context_first": [
            "gemini-1.5-pro",  # 2M tokens
            "gpt-4.1-2025-04-14",  # 1M tokens
            "gpt-5-2025-08-07",  # 400K tokens
            "claude-3-5-sonnet-20241022"  # 200K tokens
        ]
    }
    
    return strategies.get(requirements["priority"], strategies["quality_first"])

class ModelFallbackChain:
    """Implement fallback chains for reliability"""
    
    def __init__(self):
        self.fallback_chains = {
            "premium": [
                "gpt-5-2025-08-07",
                "gpt-4.1-2025-04-14",
                "claude-3-5-sonnet-20241022",
                "gemini-1.5-pro",
                "gpt-4o"
            ],
            "efficient": [
                "gpt-5-nano-2025-08-07",
                "gpt-5-mini-2025-08-07",
                "claude-3-5-haiku-20241022",
                "gpt-4o-mini",
                "gemini-1.5-flash"
            ]
        }
    
    def execute_with_fallback(self, chain_type, prompt):
        """Execute with automatic fallback"""
        
        chain = self.fallback_chains[chain_type]
        
        for model in chain:
            try:
                return self.call_model(model, prompt)
            except Exception as e:
                print(f"Model {model} failed: {e}")
                continue
        
        raise Exception("All models in fallback chain failed")

class CostMonitor:
    """Monitor and control model costs"""
    
    def __init__(self, monthly_budget: float):
        self.monthly_budget = monthly_budget
        self.current_spend = 0.0
        self.model_usage = {}
    
    def track_usage(self, model: str, tokens_in: int, tokens_out: int):
        """Track model usage and costs"""
        
        cost = self.calculate_cost(model, tokens_in, tokens_out)
        self.current_spend += cost
        
        if model not in self.model_usage:
            self.model_usage[model] = {"calls": 0, "cost": 0}
        
        self.model_usage[model]["calls"] += 1
        self.model_usage[model]["cost"] += cost
        
        # Alert if approaching budget
        if self.current_spend > self.monthly_budget * 0.8:
            self.send_budget_alert()
    
    def get_usage_report(self):
        """Generate usage report"""
        
        return {
            "total_spend": self.current_spend,
            "budget_remaining": self.monthly_budget - self.current_spend,
            "model_breakdown": self.model_usage
        }

# Before: Single model deployment
client = OpenAI(api_key="key")
response = client.chat.completions.create(
    model="gpt-4",
    messages=[...]
)

# After: Multi-model with intelligent selection
class MultiModelClient:
    def __init__(self):
        self.gateway = "https://gateway.altrum.ai/v1"
    
    def create_completion(self, messages, requirements=None):
        # Select model based on requirements
        model = self.select_optimal_model(requirements)
        
        # Create client for selected model
        client = self.create_client_for_model(model)
        
        # Execute with automatic fallback
        return self.execute_with_fallback(client, model, messages)