> ## Documentation Index
> Fetch the complete documentation index at: https://wb-21fd5541-codex-link-agent-evals-docs.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# View reasoning information

> How to return and view reasoning in your Serverless Inference responses

Reasoning models, such as [Google's Gemma 4](https://huggingface.co/google/gemma-4-31B-it), return information about their reasoning steps alongside the final answer. This page explains how to identify reasoning-capable models on Serverless Inference, where to find reasoning output in a response, and how to turn reasoning on or off for models that support toggling it. Use this guide to inspect a model's intermediate reasoning or to control whether reasoning appears in a response.

To determine whether a model supports reasoning, check the following Supported models table or the **Supported Features** section of its catalog page in the UI.

Reasoning information appears in the `reasoning` field of responses. The value of this field is `null` in the responses of non-reasoning models.

## Supported models with reasoning

The following table lists the Serverless Inference models that can return reasoning output, and how each one behaves:

* **Always on:** The model always returns reasoning output. You can't disable it.
* **Enabled by default** / **Disabled by default:** You can turn reasoning output on or off. The table shows the default when you don't specify a setting.
* **Adaptive; model chooses by default:** The model decides per request whether to return reasoning output. You can override this.

| Model ID (for API usage)                       | Reasoning support                  |
| ---------------------------------------------- | ---------------------------------- |
| `deepseek-ai/DeepSeek-V4-Flash`                | Disabled by default                |
| `deepseek-ai/DeepSeek-V4-Pro`                  | Disabled by default                |
| `google/gemma-4-31B-it`                        | Disabled by default                |
| `MiniMaxAI/MiniMax-M3`                         | Adaptive; model chooses by default |
| `MiniMaxAI/MiniMax-M2.5`                       | Always on                          |
| `moonshotai/Kimi-K2.7-Code`                    | Always on                          |
| `moonshotai/Kimi-K2.6`                         | Always on                          |
| `moonshotai/Kimi-K2.5`                         | Always on                          |
| `nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8` | Enabled by default                 |
| `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B`     | Enabled by default                 |
| `openai/gpt-oss-120b`                          | Always on                          |
| `openai/gpt-oss-20b`                           | Always on                          |
| `Qwen/Qwen3.6-35B-A3B`                         | Enabled by default                 |
| `Qwen/Qwen3.6-27B`                             | Enabled by default                 |
| `Qwen/Qwen3.5-35B-A3B`                         | Enabled by default                 |
| `Qwen/Qwen3.5-27B`                             | Enabled by default                 |
| `Qwen/Qwen3-235B-A22B-Thinking-2507`           | Always on                          |
| `zai-org/GLM-5.2`                              | Enabled by default                 |
| `zai-org/GLM-5.1`                              | Enabled by default                 |

### Models with `Always on` reasoning

If a model is listed as `Always on` in the preceding [Supported models](#supported-models) table, it always includes reasoning, and you can't disable it.

### Disable reasoning

If a model is listed as `Enabled by default` in the preceding [Supported models](#supported-models) table, you can disable reasoning to reduce token usage or simplify the response. To opt out of reasoning for a request, in `chat_template_kwargs`, set the `enable_thinking` flag to `False` (Python) or `false` (Bash). After the request completes, the response omits the reasoning content:

<Tabs>
  <Tab title="Python">
    ```python lines highlight={13-17} theme={null}
    import openai

    client = openai.OpenAI(
        base_url='https://api.inference.wandb.ai/v1',
        api_key="[YOUR-API-KEY]",  # Create an API key at https://wandb.ai/settings
    )

    response = client.chat.completions.create(
        model="google/gemma-4-31B-it",
        messages=[
            {"role": "user", "content": "3.11 and 3.8, which is greater?"}
        ],
        extra_body={
            "chat_template_kwargs": {
                "enable_thinking": False
            }
        },
    )
    ```
  </Tab>

  <Tab title="Bash">
    ```bash lines highlight={9} theme={null}
    curl https://api.inference.wandb.ai/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer [YOUR-API-KEY]" \
      -d '{
        "model": "google/gemma-4-31B-it",
        "messages": [
          { "role": "user", "content": "3.11 and 3.8, which is greater?" }
        ],
        "chat_template_kwargs": {"enable_thinking": false}
      }'
    ```
  </Tab>
</Tabs>

### Enable reasoning

If a model is listed as `Disabled by default` in the preceding [Supported models](#supported-models) table, you can enable reasoning by setting the `enable_thinking` flag to `True` (Python) or `true` (Bash) in the preceding code snippet.