---
title: Anthropic Compatible API
emoji: 🤖
colorFrom: purple
colorTo: blue
sdk: docker
pinned: false
license: apache-2.0
---

# Anthropic-Compatible API

A lightweight, CPU-based API endpoint that provides **Anthropic Messages API compatibility** using the SmolLM2-135M model.

## Features

- ✅ Full Anthropic Messages API compatibility
- ✅ Streaming support (SSE)
- ✅ Token counting endpoint
- ✅ Ultra-lightweight (135M parameters)
- ✅ CPU-optimized
- ✅ No GPU required

## API Endpoints

### Create Message
```bash
POST /v1/messages
```

### Example Request
```bash
curl -X POST "https://YOUR_SPACE.hf.space/v1/messages" \
  -H "Content-Type: application/json" \
  -H "x-api-key: your-api-key" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "smollm2-135m",
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ]
  }'
```

### Streaming Example
```bash
curl -X POST "https://YOUR_SPACE.hf.space/v1/messages" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "smollm2-135m",
    "max_tokens": 256,
    "stream": true,
    "messages": [
      {"role": "user", "content": "Tell me a short story"}
    ]
  }'
```

## SDK Compatibility

### Python
```python
import anthropic

client = anthropic.Anthropic(
    api_key="any-key",
    base_url="https://YOUR_SPACE.hf.space"
)

message = client.messages.create(
    model="smollm2-135m",
    max_tokens=256,
    messages=[{"role": "user", "content": "Hello!"}]
)
print(message.content[0].text)
```

### TypeScript/JavaScript
```typescript
import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: 'any-key',
  baseURL: 'https://YOUR_SPACE.hf.space'
});

const message = await client.messages.create({
  model: 'smollm2-135m',
  max_tokens: 256,
  messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(message.content[0].text);
```

## Model Info

- **Model**: HuggingFaceTB/SmolLM2-135M-Instruct
- **Parameters**: 135 Million
- **Optimized for**: CPU inference
- **Context Length**: 2048 tokens

## Rate Limits

This is a free CPU-based endpoint. Please be mindful of usage.

---
Built with ❤️ by Matrix Agent