npm install openai  # Use OpenAI SDK

undefined

undefined

undefined

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://openrouter.ai/api/v1',
  apiKey: process.env.OPENROUTER_API_KEY,
  defaultHeaders: {
    'HTTP-Referer': 'https://your-app.com',  // Optional
    'X-Title': 'Your App Name',              // Optional
  }
});

async function chat() {
  const completion = await client.chat.completions.create({
    model: 'anthropic/claude-3.5-sonnet',
    messages: [
      { role: 'user', content: 'Explain quantum computing in simple terms' }
    ],
  });

  console.log(completion.choices[0].message.content);
}

async function streamChat() {
  const stream = await client.chat.completions.create({
    model: 'openai/gpt-4-turbo',
    messages: [
      { role: 'user', content: 'Write a short story about AI' }
    ],
    stream: true,
  });

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

const flagshipModels = {
  claude: 'anthropic/claude-3.5-sonnet',      // Best reasoning
  gpt4: 'openai/gpt-4-turbo',                 // Best general purpose
  gemini: 'google/gemini-pro-1.5',            // Best long context
  opus: 'anthropic/claude-3-opus',            // Best complex tasks
};

const fastModels = {
  claude: 'anthropic/claude-3-haiku',         // Fastest Claude
  gpt35: 'openai/gpt-3.5-turbo',             // Fast GPT
  gemini: 'google/gemini-flash-1.5',         // Fast Gemini
  llama: 'meta-llama/llama-3.1-8b-instruct', // Fast open source
};

const budgetModels = {
  haiku: 'anthropic/claude-3-haiku',          // $0.25/$1.25 per 1M tokens
  gemini: 'google/gemini-flash-1.5',         // $0.075/$0.30 per 1M tokens
  llama: 'meta-llama/llama-3.1-8b-instruct', // $0.06/$0.06 per 1M tokens
  mixtral: 'mistralai/mixtral-8x7b-instruct', // $0.24/$0.24 per 1M tokens
};

const specializedModels = {
  vision: 'openai/gpt-4-vision-preview',     // Image understanding
  code: 'anthropic/claude-3.5-sonnet',       // Code generation
  longContext: 'google/gemini-pro-1.5',      // 2M token context
  function: 'openai/gpt-4-turbo',            // Function calling
};

interface ModelSelector {
  task: 'chat' | 'code' | 'vision' | 'function' | 'summary';
  priority: 'quality' | 'speed' | 'cost';
  maxCost?: number;  // Max cost per 1M tokens
  contextSize?: number;
}

function selectModel(criteria: ModelSelector): string {
  if (criteria.task === 'vision') {
    return 'openai/gpt-4-vision-preview';
  }

  if (criteria.task === 'code') {
    return criteria.priority === 'quality'
      ? 'anthropic/claude-3.5-sonnet'
      : 'meta-llama/llama-3.1-70b-instruct';
  }

  if (criteria.contextSize && criteria.contextSize > 100000) {
    return 'google/gemini-pro-1.5';  // 2M context
  }

  // Default selection by priority
  switch (criteria.priority) {
    case 'quality':
      return 'anthropic/claude-3.5-sonnet';
    case 'speed':
      return 'anthropic/claude-3-haiku';
    case 'cost':
      return criteria.maxCost && criteria.maxCost < 0.5
        ? 'google/gemini-flash-1.5'
        : 'anthropic/claude-3-haiku';
    default:
      return 'openai/gpt-4-turbo';
  }
}

// Usage
const model = selectModel({
  task: 'code',
  priority: 'quality',
});

async function robustStreamingChat(
  prompt: string,
  model: string = 'anthropic/claude-3.5-sonnet'
) {
  try {
    const stream = await client.chat.completions.create({
      model,
      messages: [{ role: 'user', content: prompt }],
      stream: true,
      max_tokens: 4000,
    });

    let fullResponse = '';

    for await (const chunk of stream) {
      const delta = chunk.choices[0]?.delta;

      if (delta?.content) {
        fullResponse += delta.content;
        process.stdout.write(delta.content);
      }

      // Handle function calls
      if (delta?.function_call) {
        console.log('\nFunction call:', delta.function_call);
      }

      // Check for finish reason
      if (chunk.choices[0]?.finish_reason) {
        console.log(`\n[Finished: ${chunk.choices[0].finish_reason}]`);
      }
    }

    return fullResponse;
  } catch (error) {
    if (error instanceof Error) {
      console.error('Streaming error:', error.message);
    }
    throw error;
  }
}

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ.get("OPENROUTER_API_KEY"),
)

def stream_chat(prompt: str, model: str = "anthropic/claude-3.5-sonnet"):
    stream = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": prompt}],
        stream=True,
    )

    full_response = ""
    for chunk in stream:
        if chunk.choices[0].delta.content:
            content = chunk.choices[0].delta.content
            full_response += content
            print(content, end="", flush=True)

    print()  # New line
    return full_response

import { useState } from 'react';

function StreamingChat() {
  const [response, setResponse] = useState('');
  const [isStreaming, setIsStreaming] = useState(false);

  async function handleSubmit(prompt: string) {
    setIsStreaming(true);
    setResponse('');

    try {
      const res = await fetch('https://openrouter.ai/api/v1/chat/completions', {
        method: 'POST',
        headers: {
          'Authorization': `Bearer ${process.env.OPENROUTER_API_KEY}`,
          'Content-Type': 'application/json',
        },
        body: JSON.stringify({
          model: 'anthropic/claude-3.5-sonnet',
          messages: [{ role: 'user', content: prompt }],
          stream: true,
        }),
      });

      const reader = res.body?.getReader();
      const decoder = new TextDecoder();

      while (true) {
        const { done, value } = await reader!.read();
        if (done) break;

        const chunk = decoder.decode(value);
        const lines = chunk.split('\n').filter(line => line.trim());

        for (const line of lines) {
          if (line.startsWith('data: ')) {
            const data = line.slice(6);
            if (data === '[DONE]') continue;

            try {
              const parsed = JSON.parse(data);
              const content = parsed.choices[0]?.delta?.content || '';
              setResponse(prev => prev + content);
            } catch (e) {
              // Skip invalid JSON
            }
          }
        }
      }
    } catch (error) {
      console.error('Streaming error:', error);
    } finally {
      setIsStreaming(false);
    }
  }

  return (
    <div>
      <textarea
        value={response}
        readOnly
        rows={20}
        cols={80}
        placeholder="Response will appear here..."
      />
      <button onClick={() => handleSubmit('Explain AI')}>
        {isStreaming ? 'Streaming...' : 'Send'}
      </button>
    </div>
  );
}

const tools = [
  {
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get current weather for a location',
      parameters: {
        type: 'object',
        properties: {
          location: {
            type: 'string',
            description: 'City name, e.g. San Francisco',
          },
          unit: {
            type: 'string',
            enum: ['celsius', 'fahrenheit'],
          },
        },
        required: ['location'],
      },
    },
  },
];

async function chatWithFunctions() {
  const completion = await client.chat.completions.create({
    model: 'openai/gpt-4-turbo',
    messages: [
      { role: 'user', content: 'What is the weather in Tokyo?' }
    ],
    tools,
    tool_choice: 'auto',
  });

  const message = completion.choices[0].message;

  if (message.tool_calls) {
    for (const toolCall of message.tool_calls) {
      console.log('Function:', toolCall.function.name);
      console.log('Arguments:', toolCall.function.arguments);

      // Execute function
      const args = JSON.parse(toolCall.function.arguments);
      const result = await getWeather(args.location, args.unit);

      // Send result back
      const followUp = await client.chat.completions.create({
        model: 'openai/gpt-4-turbo',
        messages: [
          { role: 'user', content: 'What is the weather in Tokyo?' },
          message,
          {
            role: 'tool',
            tool_call_id: toolCall.id,
            content: JSON.stringify(result),
          },
        ],
        tools,
      });

      console.log(followUp.choices[0].message.content);
    }
  }
}

async function multiStepFunctionCall(userQuery: string) {
  const messages = [{ role: 'user', content: userQuery }];
  let iterationCount = 0;
  const maxIterations = 5;

  while (iterationCount < maxIterations) {
    const completion = await client.chat.completions.create({
      model: 'openai/gpt-4-turbo',
      messages,
      tools,
      tool_choice: 'auto',
    });

    const message = completion.choices[0].message;
    messages.push(message);

    if (!message.tool_calls) {
      // No more function calls, return final response
      return message.content;
    }

    // Execute all function calls
    for (const toolCall of message.tool_calls) {
      const functionName = toolCall.function.name;
      const args = JSON.parse(toolCall.function.arguments);

      // Execute function (implement your function registry)
      const result = await executeFunctionCall(functionName, args);

      messages.push({
        role: 'tool',
        tool_call_id: toolCall.id,
        content: JSON.stringify(result),
      });
    }

    iterationCount++;
  }

  throw new Error('Max iterations reached');
}

import { encoding_for_model } from 'tiktoken';

interface CostEstimate {
  promptTokens: number;
  completionTokens: number;
  promptCost: number;
  completionCost: number;
  totalCost: number;
}

const modelPricing = {
  'anthropic/claude-3.5-sonnet': { input: 3.00, output: 15.00 },  // per 1M tokens
  'anthropic/claude-3-haiku': { input: 0.25, output: 1.25 },
  'openai/gpt-4-turbo': { input: 10.00, output: 30.00 },
  'openai/gpt-3.5-turbo': { input: 0.50, output: 1.50 },
  'google/gemini-flash-1.5': { input: 0.075, output: 0.30 },
};

function estimateCost(
  prompt: string,
  expectedCompletion: number,
  model: string
): CostEstimate {
  const encoder = encoding_for_model('gpt-4');  // Approximation
  const promptTokens = encoder.encode(prompt).length;
  const completionTokens = expectedCompletion;

  const pricing = modelPricing[model] || { input: 0, output: 0 };

  const promptCost = (promptTokens / 1_000_000) * pricing.input;
  const completionCost = (completionTokens / 1_000_000) * pricing.output;

  return {
    promptTokens,
    completionTokens,
    promptCost,
    completionCost,
    totalCost: promptCost + completionCost,
  };
}

// Usage
const estimate = estimateCost(
  'Explain quantum computing',
  500,  // Expected response tokens
  'anthropic/claude-3.5-sonnet'
);

console.log(`Estimated cost: $${estimate.totalCost.toFixed(4)}`);

async function budgetOptimizedChat(
  prompt: string,
  maxCostPerRequest: number = 0.01  // $0.01 max
) {
  // Estimate with expensive model
  const expensiveEstimate = estimateCost(
    prompt,
    1000,
    'anthropic/claude-3.5-sonnet'
  );

  let selectedModel = 'anthropic/claude-3.5-sonnet';

  if (expensiveEstimate.totalCost > maxCostPerRequest) {
    // Try cheaper models
    const cheapEstimate = estimateCost(
      prompt,
      1000,
      'anthropic/claude-3-haiku'
    );

    if (cheapEstimate.totalCost > maxCostPerRequest) {
      selectedModel = 'google/gemini-flash-1.5';
    } else {
      selectedModel = 'anthropic/claude-3-haiku';
    }
  }

  console.log(`Selected model: ${selectedModel}`);

  const completion = await client.chat.completions.create({
    model: selectedModel,
    messages: [{ role: 'user', content: prompt }],
  });

  return completion.choices[0].message.content;
}

async function batchProcess(prompts: string[], model: string) {
  // Process multiple prompts in parallel with rate limiting
  const concurrency = 5;
  const results = [];

  for (let i = 0; i < prompts.length; i += concurrency) {
    const batch = prompts.slice(i, i + concurrency);

    const batchResults = await Promise.all(
      batch.map(prompt =>
        client.chat.completions.create({
          model,
          messages: [{ role: 'user', content: prompt }],
          max_tokens: 500,  // Limit tokens to control cost
        })
      )
    );

    results.push(...batchResults);

    // Rate limiting delay
    if (i + concurrency < prompts.length) {
      await new Promise(resolve => setTimeout(resolve, 1000));
    }
  }

  return results;
}

const modelFallbackChain = [
  'anthropic/claude-3.5-sonnet',
  'openai/gpt-4-turbo',
  'anthropic/claude-3-haiku',
  'google/gemini-flash-1.5',
];

async function chatWithFallback(
  prompt: string,
  maxRetries: number = 3
): Promise<string> {
  for (const model of modelFallbackChain) {
    try {
      console.log(`Trying model: ${model}`);

      const completion = await client.chat.completions.create({
        model,
        messages: [{ role: 'user', content: prompt }],
        max_tokens: 2000,
      });

      return completion.choices[0].message.content || '';
    } catch (error) {
      console.warn(`Model ${model} failed:`, error);

      // Continue to next model
      if (model === modelFallbackChain[modelFallbackChain.length - 1]) {
        throw new Error('All models failed');
      }
    }
  }

  throw new Error('No models available');
}