UPIP AI API Documentation

⚡ Quick Start

Get started with the UPIP AI API in under 60 seconds:

1. Get Your API Key

Sign up for a free account (no credit card required) at upip.company/signup.html

2. Make Your First Request

curl https://upip.company/api/ai-api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen2.5:7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
            

3. Use in Your Code

// JavaScript / Node.js
const response = await fetch('https://upip.company/api/ai-api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: JSON.stringify({
    model: 'qwen2.5:7b',
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);
            

✓ OpenAI Compatible: Use the OpenAI Python library by changing just the base URL!

# Python with OpenAI library
import openai

openai.api_key = "YOUR_API_KEY"
openai.api_base = "https://upip.company/api/ai-api/v1"

response = openai.ChatCompletion.create(
  model="qwen2.5:7b",
  messages=[{"role": "user", "content": "Hello!"}]
)
            

💰 Pricing

Save 79-99% compared to OpenAI, Anthropic, and Google AI.

Plan	Price	Tokens/mo	Images/mo	Audio/mo	Rate Limit
Free	$0	100K	10	30 minutes	30 req/min
Startup	$19/mo	2M	200	600 minutes	60 req/min
Professional	$49/mo	10M	1,000	3,000 minutes	120 req/min
Enterprise	$249/mo	100M	10,000	30,000 minutes	600 req/min

💸 Real Savings Example: 100M tokens with OpenAI costs $625/month. With UPIP AI API? Just $249/month. That's $376/month in savings!

🧠 Available Models

Text Generation (Chat Completions)

qwen2.5:3b - Fast, efficient 3B parameter model
qwen2.5:7b - Balanced 7B parameter model (recommended)
llama3.2:3b - Meta's Llama 3.2 3B
phi3:3.8b - Microsoft's Phi-3 model
gemma2:9b - Google's Gemma 2 9B
mistral:7b - Mistral AI 7B
codellama:7b - Code-specialized Llama
70B+ models: llama3.3:70b, qwen2.5:72b, mixtral:8x7b

Premium Models (Cloud API)

gemini-2.0-flash-exp - Google's latest Gemini 2.0
claude-3-5-sonnet-20241022 - Anthropic's Claude 3.5

Image Generation

stable-diffusion-xl - High-quality image generation

Audio (Speech-to-Text)

whisper-large-v3 - OpenAI's Whisper model

⚡ Smart Routing: Small models (3B-7B) run on our fast GPU layer. Large models (70B+) automatically route to our dedicated inference layer for optimal performance.

📡 API Endpoints

POST /v1/chat/completions

Text generation and chat completions (OpenAI compatible)

{
  "model": "qwen2.5:7b",
  "messages": [
    {"role": "user", "content": "Hello!"}
  ],
  "max_tokens": 500,
  "temperature": 0.7
}
                

POST /v1/images/generations

Generate images with Stable Diffusion XL

{
  "prompt": "A beautiful sunset over mountains",
  "n": 1,
  "size": "1024x1024"
}
                

POST /v1/audio/transcriptions

Transcribe audio with Whisper

// Send as multipart/form-data
FormData:
  "file": audio_file.mp3
  "model": "whisper-large-v3"
                

GET /v1/models

List all available models

🔐 Authentication

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

Authorization: Bearer YOUR_API_KEY

Your API key format: upip_live_XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX

⚠️ Keep Your API Key Secret: Never expose your API key in client-side code or public repositories. Use environment variables or secure backend storage.

📦 Response Format

All responses follow the OpenAI API format with additional UPIP metadata:

{
  "id": "chatcmpl-XXXXX",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "qwen2.5:7b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 8,
    "total_tokens": 13
  },
  "upip_meta": {
    "processing_time_ms": 1234,
    "cost": "0.000013",
    "tier": "Professional",
    "layer": "Layer 2 (GPU)"
  }
}
            

⚡ Rate Limits

Rate limits vary by subscription tier:

Free: 30 requests/minute
Startup: 60 requests/minute
Professional: 120 requests/minute
Enterprise: 600 requests/minute

Rate limit information is returned in response headers:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 59
X-RateLimit-Reset: 1234567890
            

💬 Support & Resources

Email: support@upip.company
Status Page: upip.company/status
Dashboard: upip.company/dashboard
GitHub: Sample code and SDKs (coming soon)

🚀 Ready to start building? Get your free API key now!

🤖 UPIP AI API Documentation