🚀 Welcome to ZenoAI

ZenoAI provides access to 300+ state-of-the-art AI models through a simple, powerful API. Our token-based pricing ensures you only pay for what you use, with transparent billing down to the individual token.

300+ AI Models
53 Free Models
$0.0033 Starting Price
99.9% Uptime

⚡ Quick Start

1. Create Account

Sign up for a ZenoAI account to get your API key and start building with AI.

POST /accounts/create

2. Choose Model

Browse our extensive collection of AI models and choose the perfect one for your use case.

GET /v2/models

3. Start Building

Make your first API call and start integrating AI into your applications.

POST /v2/chat/pure

👤 Account Management

Creating an Account

Create your ZenoAI account to get started with API access:

# Create a new account
curl -X POST https://api.zenoai.com/accounts/create \
  -H "Content-Type: application/json" \
  -d '{
    "email": "your@email.com",
    "name": "Your Name"
  }'
Response: 
{
  "success": true,
  "account": {
    "apiKey": "zeno_abc123...",
    "accountId": "acc_xyz789...",
    "email": "your@email.com",
    "balance": 0.00,
    "currency": "USD"
  }
}

Managing Your Account

GET /accounts/me - Get account information
GET /accounts/usage - View usage statistics

🔌 Making API Requests

Authentication

All API requests require authentication using your API key in the Authorization header:

curl -X POST https://api.zenoai.com/v2/chat/pure \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json"

Chat Completion (V2 - Recommended)

Use our latest V2 API for advanced features and token-based billing:

// Simple chat request
const response = await fetch('https://api.zenoai.com/v2/chat/pure', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'anthropic/claude-sonnet-4',
    messages: [
      {
        role: 'user',
        content: 'Explain quantum computing in simple terms'
      }
    ],
    max_tokens: 1000,
    temperature: 0.7
  })
});

const data = await response.json();
Enhanced Response with Token Billing: 
{
  "response": {
    "choices": [{
      "message": {
        "content": "Quantum computing is like having a magical computer...",
        "role": "assistant"
      }
    }],
    "usage": {
      "prompt_tokens": 123,
      "completion_tokens": 456,
      "total_tokens": 579
    }
  },
  "billing": {
    "input_tokens": 123,
    "output_tokens": 456,
    "total_tokens": 579,
    "input_cost_usd": 0.000406,
    "output_cost_usd": 0.007524,
    "total_cost_usd": 0.007930,
    "remaining_balance_usd": 9.992070,
    "model_used": "anthropic/claude-sonnet-4",
    "currency": "USD",
    "is_free_model": false,
    "pricing": {
      "input_price_per_million": 3.3,
      "output_price_per_million": 16.5
    }
  },
  "success": true,
  "timestamp": "2025-01-28T12:34:56.789Z"
}

Available Endpoints

POST /v2/chat/pure - Single chat completion
POST /v2/chat/history - Chat with conversation history
GET /v2/models - List available models

🤖 Available Models

Choose from our extensive collection of AI models:

Free Models (53 available)

  • No cost to use
  • Great for testing and development
  • Popular models like Qwen, Gemma, DeepSeek
  • Full feature access
qwen/qwen3-coder:free
google/gemma-3-27b-it:free
deepseek/deepseek-r1:free

Premium Models (250+ available)

  • State-of-the-art performance
  • Token-based pricing
  • Claude, GPT-4, Grok, and more
  • Advanced reasoning capabilities
anthropic/claude-sonnet-4
openai/gpt-4o-2024-11-20
x-ai/grok-3

💡 Pro Tip: Use the /v2/models endpoint to get the complete list with current pricing.

💰 Transparent Pricing

Our token-based pricing ensures you only pay for what you use:

Free Tier

$0.00
  • 53 free models
  • No hidden costs
  • Full API access
  • Community support

Pay-Per-Use

$0.0033

per million tokens

  • 300+ premium models
  • Token-level precision
  • Real-time billing
  • Detailed usage analytics

Enterprise

Custom
  • Volume discounts
  • Priority support
  • Custom integrations
  • SLA guarantees

📊 Usage Monitoring

Real-Time Billing

Every API response includes detailed billing information:

{
  "billing": {
    "input_tokens": 123,
    "output_tokens": 456,
    "total_cost_usd": 0.007930,
    "remaining_balance_usd": 9.992070
  }
}

Account Dashboard

GET /accounts/usage - Detailed usage statistics
Usage Response: 
{
  "currentBalance": 9.99,
  "totalUsage": 15.67,
  "tokensUsed": {
    "input": 125430,
    "output": 89234,
    "total": 214664
  },
  "topModels": [
    {
      "model": "anthropic/claude-sonnet-4",
      "requests": 45,
      "cost": 12.34
    }
  ]
}

✨ Advanced Features

🔄 Conversation History

Maintain context across multiple messages with our history endpoint.

POST /v2/chat/history

🧠 Reasoning Models

Access advanced reasoning models like o1, DeepSeek-R1, and more.

openai/o1-preview
deepseek/deepseek-r1

🎨 Multimodal Support

Process text, images, and other media with multimodal models.

anthropic/claude-3.5-sonnet
openai/gpt-4o-2024-11-20

⚡ High Performance

99.9% uptime with global edge infrastructure for low latency.

< 100ms response time
Global edge network