> ## Documentation Index
> Fetch the complete documentation index at: https://doc.starrise.tech/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Sonnet 4 Thinking

> Anthropic's Claude Sonnet 4 with Extended Thinking — enhanced reasoning at Sonnet-level speed and cost.

Claude Sonnet 4 Thinking is the Extended Thinking version of Claude Sonnet 4, available through Starrise AI via OpenAI-compatible interface. Combining Sonnet's excellent balance of speed and capability with step-by-step internal reasoning enabled by default, it significantly improves accuracy on complex tasks while maintaining fast response times.

## Key Capabilities

* **OpenAI-compatible** — Drop-in replacement for the OpenAI SDK, no other code changes needed
* **Extended Thinking** — Step-by-step internal reasoning enabled by default
* **Balanced performance** — Strong reasoning capability at Sonnet-level speed and cost
* **Advanced coding** — Expert at code generation, debugging, and refactoring
* **Long context** — Supports large document processing and multi-turn conversations
* **Streaming** — Real-time token streaming via SSE

## Quick Example

<CodeGroup>
  ```bash cURL theme={null}
  curl https://ai.alad.com/v1/messages \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "claude-sonnet-4-20250514-thinking",
      "messages": [
        { "role": "user", "content": "Solve step by step: A train travels 120 km in 2 hours, then slows down and travels 80 km in 3 hours. What is the average speed for the entire journey?" }
      ]
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://ai.alad.com/v1"
  )

  response = client.chat.completions.create(
      model="claude-sonnet-4-20250514-thinking",
      messages=[
          {"role": "user", "content": "Solve step by step: A train travels 120 km in 2 hours, then slows down and travels 80 km in 3 hours. What is the average speed for the entire journey?"}
      ]
  )

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

  ```python Streaming theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://ai.alad.com/v1"
  )

  stream = client.chat.completions.create(
      model="claude-sonnet-4-20250514-thinking",
      messages=[
          {"role": "user", "content": "Prove that there are infinitely many prime numbers."}
      ],
      stream=True
  )

  for chunk in stream:
      print(chunk.choices[0].delta.content or "", end="")
  ```
</CodeGroup>

## Parameters

| Parameter     | Type           | Required | Description                                      |
| ------------- | -------------- | -------- | ------------------------------------------------ |
| `model`       | string         | Yes      | Fixed value: `claude-sonnet-4-20250514-thinking` |
| `messages`    | array          | Yes      | Array of `{ role, content }` objects             |
| `max_tokens`  | integer        | No       | Maximum number of tokens to generate             |
| `temperature` | float          | No       | `0`–`2`, controls randomness, default `1`        |
| `stream`      | boolean        | No       | Enable SSE streaming, default `false`            |
| `top_p`       | float          | No       | Nucleus sampling threshold, default `1`          |
| `stop`        | string / array | No       | Sequences where generation stops                 |

<Card title="API Reference" icon="code" href="/en/api-reference/introduction">
  View the interactive API Playground for Claude Sonnet 4 Thinking.
</Card>