sglang/docs_new/docs/advanced_features/separate_reasoning.mdx

---
title: "Reasoning Parser"
metatags:
    description: "SGLang reasoning parser: separate thinking content from output for DeepSeek R1, Qwen3, Kimi K2, GPT-OSS reasoning models."
---
SGLang supports parsing reasoning content out from "normal" content for reasoning models such as [DeepSeek R1](https://huggingface.co/deepseek-ai/DeepSeek-R1).

## Supported Models & Parsers

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <colgroup>
    <col style={{width: "25%"}} />
    <col style={{width: "25%"}} />
    <col style={{width: "25%"}} />
    <col style={{width: "25%"}} />
  </colgroup>
  <thead>
    <tr style={{borderBottom: "2px solid #d55816"}}>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Model</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Reasoning tags</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Parser</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Notes</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[DeepSeek‑R1 series](https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`<think>` … `</think>`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`deepseek-r1`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Supports all variants (R1, R1-0528, R1-Distill)</td>
    </tr>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[DeepSeek‑V3 series](https://huggingface.co/deepseek-ai/DeepSeek-V3.1)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`<think>` … `</think>`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`deepseek-v3`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Including [DeepSeek‑V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp). Supports `thinking` parameter</td>
    </tr>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[Standard Qwen3 models](https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`<think>` … `</think>`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`qwen3`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Supports `enable_thinking` parameter</td>
    </tr>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[Qwen3-Thinking models](https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`<think>` … `</think>`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`qwen3` or `qwen3-thinking`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Always generates thinking content</td>
    </tr>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[Kimi K2 Thinking](https://huggingface.co/moonshotai/Kimi-K2-Thinking)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`◁think▷` … `◁/think▷`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`kimi_k2`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Uses special thinking delimiters. Also requires `--tool-call-parser kimi_k2` for tool use.</td>
    </tr>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[GPT OSS](https://huggingface.co/openai/gpt-oss-120b)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`&lt;|channel|&gt;analysis&lt;|message|&gt;` … `&lt;|end|&gt;`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`gpt-oss`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>N/A</td>
    </tr>
  </tbody>
</table>
### Model-Specific Behaviors

**DeepSeek-R1 Family:**
- DeepSeek-R1: No `<think>` start tag, jumps directly to thinking content
- DeepSeek-R1-0528: Generates both `<think>` start and `</think>` end tags
- Both are handled by the same `deepseek-r1` parser

**DeepSeek-V3 Family:**
- DeepSeek-V3.1/V3.2: Hybrid model supporting both thinking and non-thinking modes, use the `deepseek-v3` parser and `thinking` parameter (NOTE: not `enable_thinking`)

**Qwen3 Family:**
- Standard Qwen3 (e.g., Qwen3-2507): Use `qwen3` parser, supports `enable_thinking` in chat templates
- Qwen3-Thinking (e.g., Qwen3-235B-A22B-Thinking-2507): Use `qwen3` or `qwen3-thinking` parser, always thinks

**Kimi K2:**
- Kimi K2 Thinking: Uses special `◁think▷` and `◁/think▷` tags. For agentic tool use, also specify `--tool-call-parser kimi_k2`.

**GPT OSS:**
- GPT OSS: Uses special `<|channel|>analysis<|message|>` and `<|end|>` tags


## Usage

### Launching the Server


Specify the `--reasoning-parser` option.



```python Example
import requests
from openai import OpenAI
from sglang.test.doc_patch import launch_server_cmd
from sglang.utils import wait_for_server, print_highlight, terminate_process

server_process, port = launch_server_cmd(
    "python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-7B --host 0.0.0.0 --reasoning-parser deepseek-r1 --log-level warning"
)

wait_for_server(f"http://localhost:{port}")
```

Note that `--reasoning-parser` defines the parser used to interpret responses.


### OpenAI Compatible API

Using the OpenAI compatible API, the contract follows the [DeepSeek API design](https://api-docs.deepseek.com/guides/reasoning_model) established with the release of DeepSeek-R1:

- `reasoning_content`: The content of the CoT.
- `content`: The content of the final answer.



```python Example
# Initialize OpenAI-like client
client = OpenAI(api_key="None", base_url=f"http://0.0.0.0:{port}/v1")
model_name = client.models.list().data[0].id

messages = [
    {
        "role": "user",
        "content": "What is 1+3?",
    }
]
```

#### Non-Streaming Request



```python Example
response_non_stream = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.6,
    top_p=0.95,
    stream=False,  # Non-streaming
    extra_body={"separate_reasoning": True},
)
print_highlight("==== Reasoning ====")
print_highlight(response_non_stream.choices[0].message.reasoning_content)

print_highlight("==== Text ====")
print_highlight(response_non_stream.choices[0].message.content)
```

#### Streaming Request



```python Example
response_stream = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.6,
    top_p=0.95,
    stream=True,  # Non-streaming
    extra_body={"separate_reasoning": True},
)

reasoning_content = ""
content = ""
for chunk in response_stream:
    if chunk.choices[0].delta.content:
        content += chunk.choices[0].delta.content
    if chunk.choices[0].delta.reasoning_content:
        reasoning_content += chunk.choices[0].delta.reasoning_content

print_highlight("==== Reasoning ====")
print_highlight(reasoning_content)

print_highlight("==== Text ====")
print_highlight(content)
```

Optionally, you can buffer the reasoning content to the last reasoning chunk (or the first chunk after the reasoning content).



```python Example
response_stream = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.6,
    top_p=0.95,
    stream=True,  # Non-streaming
    extra_body={"separate_reasoning": True, "stream_reasoning": False},
)

reasoning_content = ""
content = ""
for chunk in response_stream:
    if chunk.choices[0].delta.content:
        content += chunk.choices[0].delta.content
    if chunk.choices[0].delta.reasoning_content:
        reasoning_content += chunk.choices[0].delta.reasoning_content

print_highlight("==== Reasoning ====")
print_highlight(reasoning_content)

print_highlight("==== Text ====")
print_highlight(content)
```

The reasoning separation is enable by default when specify .
**To disable it, set the `separate_reasoning` option to `False` in request.**



```python Example
response_non_stream = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.6,
    top_p=0.95,
    stream=False,  # Non-streaming
    extra_body={"separate_reasoning": False},
)

print_highlight("==== Original Output ====")
print_highlight(response_non_stream.choices[0].message.content)
```

### SGLang Native API



```python Example
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")
input = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True, return_dict=False
)

gen_url = f"http://localhost:{port}/generate"
gen_data = {
    "text": input,
    "sampling_params": {
        "skip_special_tokens": False,
        "max_new_tokens": 1024,
        "temperature": 0.6,
        "top_p": 0.95,
    },
}
gen_response = requests.post(gen_url, json=gen_data).json()["text"]

print_highlight("==== Original Output ====")
print_highlight(gen_response)

parse_url = f"http://localhost:{port}/separate_reasoning"
separate_reasoning_data = {
    "text": gen_response,
    "reasoning_parser": "deepseek-r1",
}
separate_reasoning_response_json = requests.post(
    parse_url, json=separate_reasoning_data
).json()
print_highlight("==== Reasoning ====")
print_highlight(separate_reasoning_response_json["reasoning_text"])
print_highlight("==== Text ====")
print_highlight(separate_reasoning_response_json["text"])
```


```python Example
terminate_process(server_process)
```

### Offline Engine API



```python Example
import sglang as sgl
from sglang.srt.parser.reasoning_parser import ReasoningParser
from sglang.utils import print_highlight

llm = sgl.Engine(model_path="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")
input = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True, return_dict=False
)
sampling_params = {
    "max_new_tokens": 1024,
    "skip_special_tokens": False,
    "temperature": 0.6,
    "top_p": 0.95,
}
result = llm.generate(prompt=input, sampling_params=sampling_params)

generated_text = result["text"]  # Assume there is only one prompt

print_highlight("==== Original Output ====")
print_highlight(generated_text)

parser = ReasoningParser("deepseek-r1")
reasoning_text, text = parser.parse_non_stream(generated_text)
print_highlight("==== Reasoning ====")
print_highlight(reasoning_text)
print_highlight("==== Text ====")
print_highlight(text)
```


```python Example
llm.shutdown()
```

## Supporting New Reasoning Model Schemas

For future reasoning models, you can implement the reasoning parser as a subclass of `BaseReasoningFormatDetector` in `python/sglang/srt/reasoning_parser.py` and specify the reasoning parser for new reasoning model schemas accordingly.