# Claude extended thinking: thinking, budget_tokens, adaptive and the OpenAI-compatible format

Source: https://ofox.ai/docs/develop/models/claude/thinking

This page explains how to enable Claude's extended thinking and read the thinking content. For model IDs and endpoints, see the [Claude family overview](https://ofox.ai/docs/develop/models/claude).

**Key point**:Pass thinking on the native API and a reasoning object on the OpenAI-compatible API. Do not set temperature when thinking is enabled.

Extended thinking lets the model reason before answering, which helps with math, code and multi-step analysis. In our tests, the following models reliably returned thinking content on the default provider: Opus 5.5, Opus 5, Opus 4.8, Opus 4.6, Sonnet 4.6, Haiku 5.5, Haiku 4.5, Fable 5.

## Anthropic-native API
There are two modes:

| Mode | Syntax | Notes |
|---|---|---|
| Fixed budget | `"thinking": {"type": "enabled", "budget_tokens": 2000}` | `budget_tokens` must be at least 1024 and less than `max_tokens` |
| Adaptive | `"thinking": {"type": "adaptive"}` | The model decides how deeply to think; tune it with settings such as `"output_config": {"effort": "low"}` |

**Python**

```python filename="claude_thinking.py"
import os
import anthropic

client = anthropic.Anthropic(base_url="https://api.ofox.ai/anthropic", api_key=os.environ["OFOX_API_KEY"])

message = client.messages.create(
    model="anthropic/claude-opus-5.5",
    max_tokens=4000,
    thinking={"type": "enabled", "budget_tokens": 2000},
    messages=[{"role": "user", "content": "A bat and a ball cost $1.10 in total. The bat costs $1 more than the ball. How much does the ball cost?"}],
)
for block in message.content:
    if block.type == "thinking":
        print("[Thinking]", block.thinking)
    elif block.type == "text":
        print("[Answer]", block.text)
```

**cURL**

```bash filename="Terminal"
curl https://api.ofox.ai/anthropic/v1/messages \
  -H "x-api-key: $OFOX_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5.5",
    "max_tokens": 4000,
    "thinking": {"type": "enabled", "budget_tokens": 2000},
    "messages": [{"role": "user", "content": "A bat and a ball cost $1.10 in total. The bat costs $1 more than the ball. How much does the ball cost?"}]
  }'
```

- In the response `content`, `thinking` blocks come first, followed by `text` blocks. Each `thinking` block carries a `signature`, which must be passed back unchanged in multi-turn tool calling.
- When streaming, thinking content arrives as `thinking_delta` events, followed by a single `signature_delta` event, and then `text_delta` begins.
- When thinking is enabled, do not set `temperature` (or set it to 1), and do not set `top_k`.
- Tokens spent on thinking count toward `output_tokens` and are billed at the output rate.

## OpenAI-compatible API
Enable it with a `reasoning` object, where `max_tokens` is the thinking budget:

```python filename="claude_thinking_openai.py"
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.ofox.ai/v1", api_key=os.environ["OFOX_API_KEY"])

resp = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.6",
    max_tokens=4000,
    extra_body={"reasoning": {"max_tokens": 2000}},
    messages=[{"role": "user", "content": "A bat and a ball cost $1.10 in total. The bat costs $1 more than the ball. How much does the ball cost?"}],
)
msg = resp.choices[0].message
details = getattr(msg, "reasoning_details", None) or []
print("[Thinking]", "".join(d.get("text", "") for d in details))
print("[Answer]", msg.content)
```

- In non-streaming responses, thinking content is in `message.reasoning_details`; concatenate the `text` of each item in order.
- In streaming responses, thinking content is in `delta.reasoning_content`.

For other errors, see [Common errors](https://ofox.ai/docs/develop/models/claude#errors).