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

# Anthropic Extended Thinking

> Configure reasoning token budgets and capture thinking blocks on Claude models.

Extended Thinking on the `/anthropic/v1/messages` endpoint allows [Claude](https://www.anthropic.com/claude?utm_source=neosantara-docs\&utm_medium=referral) models to deeply reason through complex tasks before producing answers. You control reasoning token expenditure via the `thinking` parameter object.

<CodeGroup>
  ```python Python (Anthropic SDK) icon="python" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  from anthropic import Anthropic
  import os

  client = Anthropic(
      base_url="https://api.neosantara.xyz/anthropic",
      api_key=os.environ["NEOSANTARA_API_KEY"]
  )

  response = client.messages.create(
      model="claude-sonnet-4-6",
      max_tokens=4096,
      thinking={
          "type": "enabled",
          "budget_tokens": 2048
      },
      messages=[
          {"role": "user", "content": "How many 'r' letters are in the word 'strawberry'?"}
      ]
  )

  for block in response.content:
      if block.type == "thinking":
          print(f"[Thinking Process]:\n{block.thinking}\n")
      elif block.type == "text":
          print(f"[Final Answer]:\n{block.text}")
  ```

  ```bash cURL icon="terminal" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  curl -X POST https://api.neosantara.xyz/anthropic/v1/messages \
    -H "x-api-key: $NEOSANTARA_API_KEY" \
    -H "anthropic-version: 2023-06-01" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "claude-sonnet-4-6",
      "max_tokens": 4096,
      "thinking": {
        "type": "enabled",
        "budget_tokens": 2048
      },
      "messages": [
        {"role": "user", "content": "How many r in strawberry?"}
      ]
    }'
  ```
</CodeGroup>

## The `thinking` Parameter Rules

* **`max_tokens` Must Exceed Budget:** `max_tokens` must always be strictly greater than `budget_tokens` to ensure sufficient room for text completion.
* **Minimum Budget Limit:** The minimum value for `budget_tokens` is 1024 tokens.
* **Response Block Structure:** Responses emit an ordered block list where `type: "thinking"` precedes `type: "text"`.

## Next Steps

| Task                  | Guide                                                           |
| :-------------------- | :-------------------------------------------------------------- |
| Anthropic Tool Use    | [Anthropic Tool Use](/en/gateway/anthropic-messages/tool-use)   |
| Anthropic Streaming   | [Anthropic Streaming](/en/gateway/anthropic-messages/streaming) |
| OpenAI Chat Reasoning | [Model Reasoning](/en/gateway/chat-completions/reasoning)       |


## Related topics

- [Anthropic Messages API](/en/gateway/anthropic-messages.md)
- [Model Reasoning](/en/gateway/chat-completions/reasoning.md)
- [Responses API Reasoning](/en/gateway/responses-api/reasoning.md)