# Disabling or reducing \<think\>...\</think\> content

**URL:** <https://community.perplexity.ai/t/disabling-or-reducing-think-think-content/2573>\
**Category:** General\
**Created:** [November 11, 2025, 8:34pm UTC](https://community.perplexity.ai/t/disabling-or-reducing-think-think-content/2573 "2025-11-11T20:34:52Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Dmytro\_Lopatiuk](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/dmytro_lopatiuk/32/1768_2.png) [@Dmytro\_Lopatiuk](https://community.perplexity.ai/u/Dmytro_Lopatiuk)\
**Post date:** [November 11, 2025, 8:34pm UTC](https://community.perplexity.ai/t/disabling-or-reducing-think-think-content/2573/1 "2025-11-11T20:34:52Z")

</div>

Hello, everyone.

The question is, is it possible to somehow influence the length of the content returned in think tag, or disable it altogether and not return it in order to get the result of other content faster?

I tried to use this through a prompt, but I don’t get any effect. It seems that prompts are not always taken into account when generating the answer.

```auto
        const options = {
      search_mode: searchMode,
      ...(searchAfterDate && { search_after_date_filter: searchAfterDate }),
      ...(searchBeforeDate && { search_before_date_filter: searchBeforeDate }),
      temperature: 0.7,
      response_format: {
        type: 'json_schema',
        json_schema: {
          schema: configModel.schema,
        },
      },
    };

    const result = streamText({
      model: myPerplexity('sonar-deep-research'),
      messages: [
        {
          role: 'system',
          content: configModel.prompt,
        },
        ...convertToModelMessages(messages),
      ],
      providerOptions: {
        perplexity: options,
      },
    });

```