OpenRouter - Unified AI API Gateway

Overview

OpenRouter provides a single API to access 200+ language models from OpenAI, Anthropic, Google, Meta, Mistral, and more. It offers intelligent routing, streaming, cost optimization, and standardized OpenAI-compatible interface.

Key Features:

• Access 200+ models through one API
• OpenAI-compatible interface (drop-in replacement)
• Intelligent model routing and fallbacks
• Real-time streaming responses
• Cost tracking and optimization
• Model performance analytics
• Function calling support
• Vision model support

Pricing Model:

• Pay-per-token (no subscriptions)
• Volume discounts available
• Free tier with credits
• Per-model pricing varies

Installation:

npm install openai  # Use OpenAI SDK
# or
pip install openai  # Python

Quick Start

1. Get API Key

# Sign up at https://openrouter.ai/keys
export OPENROUTER_API_KEY="sk-or-v1-..."

2. Basic Chat Completion

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);
}

3. Streaming Response

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);
  }
}

Model Selection Strategy

Available Model Categories

Flagship Models (Highest Quality):

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
};

Fast Models (Low Latency):

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
};

Cost-Optimized Models:

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
};

Specialized Models:

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
};

Model Selection Logic

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',
});

Streaming Implementation

TypeScript Streaming with Error Handling

async function robustStreamingChat(
  prompt: string,
  model: string = 'anthropic/claude-3.5-sonnet'
) {
  try {
    const stream = await client.chat.completions.create({
      model
how to use openrouter
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use openrouter on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add openrouter
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/bobmatnyc/claude-mpm-skills --skill openroutercopy
The skills CLI fetches openrouter from GitHub repository bobmatnyc/claude-mpm-skills and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/openrouter
Reload or restart Cursor to activate openrouter. Access the skill through slash commands (e.g., /openrouter) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?