---
title: Scira AI Reverse API
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit
app_port: 7860
---

# Scira AI Reverse API

A FastAPI server that provides OpenAI-compatible endpoints for Scira AI with advanced rate limiting bypass features.

## 🚀 Features

- ✅ **Full OpenAI Compatibility** - Drop-in replacement for OpenAI API
- ✅ **Streaming Support** - Real-time SSE responses
- ✅ **Function Calling** - Complete tool calling support
- ✅ **Rate Limiting Bypass** - Proxy rotation and header spoofing
- ✅ **FastAPI Framework** - High performance async API

## 📡 API Endpoints

### OpenAI-Compatible
- `POST /v1/chat/completions` - Chat completions with streaming
- `GET /v1/models` - List available models

### Legacy Scira
- `POST /api/search` - Direct Scira API compatibility
- `GET /health` - Health check
- `GET /` - API information

## 🔧 Usage

### Basic Chat
```bash
curl -X POST "https://your-space.hf.space/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "scira-5-mini",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
```

### Streaming
```bash
curl -X POST "https://your-space.hf.space/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "scira-5-mini",
    "messages": [
      {"role": "user", "content": "Tell me a story"}
    ],
    "stream": true
  }'
```

### Function Calling
```bash
curl -X POST "https://your-space.hf.space/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "scira-5-mini",
    "messages": [
      {"role": "user", "content": "What is the weather?"}
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get weather for a location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {"type": "string"}
            },
            "required": ["location"]
          }
        }
      }
    ]
  }'
```

## 🔑 Configuration

The API uses environment variables for configuration. Set these in your Hugging Face Space settings:

- `SCIRA_SESSION_TOKEN` - Your Scira session token
- `SCIRA_POSTHOG_TOKEN` - Your PostHog token
- `PROXY_HOST` - Proxy host (optional)
- `PROXY_USERNAME` - Proxy username (optional)
- `PROXY_PASSWORD` - Proxy password (optional)

## 🛡️ Rate Limiting Features

- **Proxy Rotation** - Residential proxy support
- **Header Spoofing** - Randomized User-Agent and browser headers
- **IP Spoofing** - X-Forwarded-For randomization
- **Request Throttling** - Random delays between requests

## 📊 Supported Parameters

All OpenAI parameters are supported:
- `model`, `messages`, `max_tokens`
- `temperature`, `top_p`, `presence_penalty`
- `stream`, `tools`, `tool_choice`
- `stop`, `frequency_penalty`, `logit_bias`

## 🔗 Integration

### Python with OpenAI Library
```python
import openai

openai.api_base = "https://your-space.hf.space/v1"
openai.api_key = "dummy"

response = openai.ChatCompletion.create(
    model="scira-5-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)
```

### JavaScript
```javascript
const response = await fetch('https://your-space.hf.space/v1/chat/completions', {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'scira-5-mini',
    messages: [{role: 'user', content: 'Hello!'}]
  })
});
```

## ⚠️ Important Notes

- This is for educational and research purposes
- Configure valid session tokens for proper functionality
- Respect Scira AI's terms of service
- Rate limiting helps avoid detection but doesn't guarantee it

## 📄 License

MIT License - See LICENSE file for details.