GenXis API Documentation

Authorization: Bearer YOUR_API_KEY

{
  "model": "genxis-supreme",
  "messages": [
    {
      "role": "user",
      "content": "What's the latest news about AI developments?"
    }
  ],
  "max_tokens": 500,
  "r5_aware": true
}

{
  "id": "genxis-chat-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "genxis-supreme",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Based on real-time data from January 2025, here are the latest AI developments: OpenAI announced GPT-5 preview, Google released Gemini Ultra 2.0, and several breakthrough papers on AGI safety were published this week. The AI industry is seeing unprecedented growth with $50B in funding this quarter alone.",
        "r5_sources": [
          "TechCrunch - AI News",
          "ArXiv Recent Papers",
          "Venture Capital Reports"
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 87,
    "total_tokens": 102
  },
  "r5_aware": true,
  "real_time_data": true
}

{
  "model": "genxis-supreme",           // Required: Model to use
  "messages": [                       // Required: Conversation messages
    {
      "role": "user",
      "content": "Your message here"
    }
  ],
  "max_tokens": 1000,                 // Optional: Max response tokens
  "temperature": 0.7,                 // Optional: 0.0-2.0, creativity level
  "stream": false,                    // Optional: Stream response
  "r5_aware": true                    // Optional: Enable real-time data
}

{
  "id": "genxis-chat-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "genxis-supreme",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "AI response with real-time data...",
        "r5_sources": ["Source 1", "Source 2"]  // When R5-Aware enabled
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 87,
    "total_tokens": 102
  },
  "r5_aware": true,                   // Indicates real-time data used
  "real_time_data": true
}

{
  "status": "healthy",
  "timestamp": 1704067200,
  "version": "1.0.0",
  "services": {
    "database": "healthy",
    "mistral_agent": "healthy"
  },
  "stats": {
    "total_users": 1250
  }
}

// Enable R5-Aware for real-time intelligence
{
  "model": "genxis-supreme",
  "messages": [...],
  "r5_aware": true  // Adds real-time data capabilities
}

// Using OpenAI JavaScript SDK
import OpenAI from 'openai';

const genxis = new OpenAI({
  apiKey: 'YOUR_GENXIS_API_KEY',
  baseURL: 'https://genxis.com/portal/api/v1'
});

async function chat() {
  const completion = await genxis.chat.completions.create({
    model: 'genxis-supreme',
    messages: [
      { role: 'user', content: 'What are the latest AI trends?' }
    ],
    r5_aware: true  // Enable real-time data
  });

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

# Using OpenAI Python SDK
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GENXIS_API_KEY",
    base_url="https://genxis.com/portal/api/v1"
)

response = client.chat.completions.create(
    model="genxis-model-l",  # FREE R5-Aware included
    messages=[
        {"role": "user", "content": "Analyze current market trends"}
    ],
    max_tokens=500
)

print(response.choices[0].message.content)

curl -X POST https://genxis.com/portal/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GENXIS_API_KEY" \
  -d '{
    "model": "genxis-lite",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python function to calculate fibonacci"
      }
    ],
    "max_tokens": 300
  }'

## GenXis AI Platform Integration

**API Configuration:**
- Base URL: https://genxis.com/portal/api/v1
- API Key: [USER_API_KEY_HERE]
- Compatible with: OpenAI SDK format
- Authentication: Bearer token in Authorization header

**Available Models:**
- genxis-lite: Fast responses ($4 input/$16 output per 1M tokens)
- genxis-model-l: Balanced performance + FREE R5-Aware ($10 input/$40 output per 1M tokens)
- genxis-supreme: Near-superintelligence ($20 input/$80 output per 1M tokens)

**Special Features:**
- R5-Aware: Add "r5_aware": true for real-time data (FREE with model-l, +$2/$8 for others)
- Real-time intelligence: Access to current information beyond training data
- Source attribution: Responses include data sources when using R5-Aware

**Rate Limits:**
- Subject to fair use policy
- Generous limits based on subscription tier
- Bonus tokens included with all paid plans

**Example Request:**
```json
{
  "model": "genxis-supreme",
  "messages": [{"role": "user", "content": "Your prompt here"}],
  "max_tokens": 500,
  "r5_aware": true
}
```

**Integration Notes:**
- Use any OpenAI-compatible library/SDK
- Replace OpenAI base_url with GenXis endpoint
- Use your GenXis API key instead of OpenAI key
- Enable r5_aware for real-time capabilities
- Model-L includes R5-Aware at no extra cost