README.md

---
title: Free Coding API
emoji: 🚀
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit
---

# 🚀 Free Coding API

**OpenAI & Anthropic Compatible API for Coding Tasks**

Built with skills, not money! This is a free, open-source API endpoint that runs on HuggingFace Spaces, providing coding assistance similar to OpenAI Codex and Claude Code.

## Features

- ✅ **OpenAI API Compatible** (`/v1/chat/completions`)
- ✅ **Anthropic API Compatible** (`/v1/messages`)
- ✅ **Streaming Support** (SSE)
- ✅ **Coding Optimized** (Qwen2.5-Coder model)
- ✅ **100% Free** (Runs on HF Spaces free tier)

## Quick Start

### Using OpenAI SDK

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://YOUR-SPACE.hf.space/v1",
    api_key="sk-free-coding-api"
)

response = client.chat.completions.create(
    model="gpt-4",  # Mapped to Qwen2.5-Coder
    messages=[
        {"role": "system", "content": "You are an expert Python developer."},
        {"role": "user", "content": "Write a function to find prime numbers"}
    ],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
```

### Using Anthropic SDK

```python
import anthropic

client = anthropic.Anthropic(
    base_url="https://YOUR-SPACE.hf.space",
    api_key="sk-free-coding-api"
)

response = client.messages.create(
    model="claude-3-sonnet",  # Mapped to Qwen2.5-Coder
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Write a REST API in FastAPI"}
    ]
)

print(response.content[0].text)
```

### Using cURL

```bash
# OpenAI format
curl -X POST https://YOUR-SPACE.hf.space/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-free-coding-api" \
  -d '{
    "model": "gpt-4",
    "messages": [{"role": "user", "content": "Hello, write Python code"}]
  }'

# Anthropic format
curl -X POST https://YOUR-SPACE.hf.space/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-free-coding-api" \
  -d '{
    "model": "claude-3-sonnet",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello, write Python code"}]
  }'
```

## API Endpoints

| Endpoint | Method | Description |
|----------|--------|-------------|
| `/v1/chat/completions` | POST | OpenAI-compatible chat |
| `/v1/messages` | POST | Anthropic-compatible messages |
| `/v1/models` | GET | List available models |
| `/health` | GET | Health check |
| `/docs` | GET | Swagger UI documentation |

## Supported Models

All model names are aliases mapped to `Qwen2.5-Coder-1.5B-Instruct`:

**OpenAI aliases:** `gpt-4`, `gpt-4-turbo`, `gpt-3.5-turbo`, `codex`, `code-davinci-002`

**Anthropic aliases:** `claude-3-opus`, `claude-3-sonnet`, `claude-3-haiku`, `claude-3-5-sonnet`, `claude-code`

## Environment Variables

| Variable | Default | Description |
|----------|---------|-------------|
| `MODEL_ID` | `Qwen/Qwen2.5-Coder-1.5B-Instruct` | HuggingFace model to use |
| `API_KEY` | `sk-free-coding-api` | API key for authentication |

## Limitations

Running on HF Spaces free tier:
- **CPU only** (2 vCPU, 16GB RAM)
- **Response time**: 10-30 seconds for typical requests
- **Max context**: ~4K tokens
- **Best for**: Code generation, debugging, explanations

## Deploy Your Own

1. Fork this Space
2. (Optional) Set environment variables in Space Settings
3. Your API is ready at `https://YOUR-USERNAME-YOUR-SPACE.hf.space`

## License

MIT License - Build with skills, not money! 🚀