### Chat Completions API

Source: https://github.com/skyworkai/skyclaw/blob/main/index.html

This snippet demonstrates how to use the chat completions endpoint to interact with the SkyClaw models. It shows both cURL and Python SDK examples.

```APIDOC
## Chat Completions API

### Description
This endpoint allows you to send messages to the SkyClaw models and receive a text completion. It supports various roles like 'user', 'system', and 'assistant' for conversational interactions.

### Method
`POST`

### Endpoint
`/v1/chat/completions`

### Parameters
#### Request Body
- **model** (string) - Required - The ID of the model to use for completion (e.g., `skywork-ai/skyclaw-v1` or `skywork-ai/skyclaw-v1-lite`).
- **messages** (array) - Required - A list of message objects, where each object has a `role` (string) and `content` (string).

### Request Example (cURL)
```bash
curl https://api.apifree.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $APIFREE_API_KEY" \
  -d '{
    "model": "skywork-ai/skyclaw-v1",
    "messages": [
      {"role": "user", "content": "Hello, SkyClaw!"}
    ]
  }'
```

### Request Example (Python SDK)
```python
from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.apifree.ai/v1"
)

response = client.chat.completions.create(
    model="skywork-ai/skyclaw-v1",
    messages=[
        {"role": "user", "content": "Hello, SkyClaw!"}
    ]
)
print(response.choices[0].message.content)
```

### Response
#### Success Response (200)
- **choices** (array) - A list of completion choices. Each choice contains a `message` object with `role` and `content`.

#### Response Example
```json
{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hello there! How can I help you today?"
      }
    }
  ]
}
```
```

--------------------------------

### Call SkyClaw API with Python OpenAI SDK

Source: https://github.com/skyworkai/skyclaw/blob/main/index.html

This Python script demonstrates how to use the OpenAI SDK to interact with the SkyClaw API. Replace 'your-api-key' with your actual API key and set the base URL.

```python
from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.apifree.ai/v1"
)

response = client.chat.completions.create(
    model="skywork-ai/skyclaw-v1",
    messages=[
        {"role": "user", "content": "Hello, SkyClaw!"}
    ]
)
print(response.choices[0].message.content)
```

--------------------------------

### Call SkyClaw API with cURL

Source: https://github.com/skyworkai/skyclaw/blob/main/index.html

Use this cURL command to send a chat completion request to the SkyClaw API. Ensure you replace '$APIFREE_API_KEY' with your actual API key.

```shell
curl https://api.apifree.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $APIFREE_API_KEY" \
  -d '{
    "model": "skywork-ai/skyclaw-v1",
    "messages": [
      {"role": "user", "content": "Hello, SkyClaw!"}
    ]
  }'
```

--------------------------------

### SkyClaw-v1.0 BibTeX Citation

Source: https://github.com/skyworkai/skyclaw/blob/main/README.md

Use this BibTeX entry when referencing SkyClaw-v1.0 in your publications. It includes the title, authors, year, month, and URL for the model.

```bibtex
@misc{skyclaw2026,
  title={SkyClaw-v1.0: A Million-Context Agent Model at Ultra-Low Cost},
  author={Peiyu Wang and Min Zou and Liang Zeng and Wei Shen and Peng Cheng and Haoran Zhang and Yu Cheng and Yang Liu},
  year={2026},
  month={May},
  howpublished={\url{https://skyworkai.github.io/skyclaw/}},
  url={https://skyworkai.github.io/skyclaw/},
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.