Skip to content
Granola Help Center home
Granola Help Center home

Understanding model selection in Granola chat

Granola chat lets you choose between different AI models depending on what you’re working on. You can either let Granola automatically pick the best model, or manually select a standard or thinking model for more control.

Auto model selection

When model selection is set to Auto, Granola automatically chooses the best model based on your chat context so you don’t have to think about it.

Screenshot 2026-01-13 at 17.43.41.png

  • For single-meeting chats (during or after a specific meeting), Auto uses GPT‑5.1

    Screenshot 2026-01-13 at 17.39.32.png

  • For multi-meeting or global chats (e.g. homepage chat, folder chats), Auto uses Claude 4 Sonnet

    Screenshot 2026-01-13 at 17.42.44.png

This helps you get fast, relevant answers whether you’re focused on one meeting or working across multiple meetings.

Standard models

Standard models are general-purpose options designed for everyday tasks where you want quick, high-quality responses.

Standard models in Granola include:

  • Sonnet 4.5 (Anthropic / Claude)

    • Best for fast, general-purpose responses across many topics

  • GPT‑5.1 (OpenAI)

    • Best for quick answers to meeting-specific questions

  • GPT‑4.1 (OpenAI)

    • Best for fast responses on simpler tasks

When to use standard models

Standard models are ideal when you need:

  • Quick questions answered about a meeting

  • Action items extracted from a call

  • Simple summaries of what was discussed

  • Everyday drafting and editing tasks that don’t require deep reasoning

Thinking models

Thinking models are advanced reasoning models that provide deeper, step-by-step analysis. They are available on Business or Enterprise plans only.

Thinking models in Granola include:

  • Sonnet 4.5 Thinking (Anthropic / Claude)

    • Best for complex analysis that benefits from visible, step-by-step reasoning

  • Opus 4.5 (Anthropic / Claude)

    • Best for the most sophisticated reasoning and really complex problems

  • Gemini 3 Pro (Google)

    • Best for deep analysis and nuanced reasoning

  • GPT‑5.1 Thinking (OpenAI)

    • Best for complex reasoning tasks where you want more careful thought

How thinking models work

Thinking models can show you how they arrived at an answer through an expandable reasoning view.

You’ll see a “Thought for Xs” indicator (where X is a number of seconds). This means the model is doing step-by-step reasoning in the background, and you can expand that indicator to view the reasoning process.

This is especially useful when you want to understand or audit how the AI reached its conclusion.

Screenshot 2026-01-13 at 17.54.05.png

When to use thinking models

Use thinking models when:

  • You’re doing complex analysis or strategy work

  • You’re exploring nuanced tradeoffs or scenarios

  • You want to see the AI’s reasoning process, not just the final answer

  • You’re working on high-stakes or intricate problems where transparency matters

Note: Thinking models require a paid subscription (Business or Enterprise).

Usage tips and best practices

This section covers general guidance for choosing the right model in chat.

General recommendations

In most cases, you don’t need to pick a model manually:

  • Leave model selection on Auto unless you have a specific reason to choose a particular model

  • Use standard models for:

    • Quick questions

    • Action item extraction

    • Simple summaries or straightforward tasks

  • Use thinking models for:

    • Complex analysis or strategy questions

    • Situations where you care about how the AI reasoned through the answer

Example use cases

Some common ways to use each model type:

  • Standard models

    • Summarize a single meeting

    • Pull out decisions and next steps

    • Draft a short follow-up message based on a call

    • Answer “what did we say about X?” for a specific meeting

  • Thinking models

    • Compare multiple meetings to derive themes or recommendations

    • Plan strategy based on several stakeholder conversations

    • Analyze risks, tradeoffs, or options using detailed reasoning

    • Understand why a particular recommendation is being made

Troubleshooting and common questions

This section addresses common issues and what to try.

I’m not sure which model to pick

  • Keep the setting on Auto so Granola selects the best model for your context

  • Manually switch to a thinking model only when you know you need deeper reasoning or visible step-by-step thinking

I don’t see thinking models as an option

  • Thinking models are available only on Business or Enterprise plans

  • If you don’t see them:

    • Check which plan your workspace is on

    • Contact your admin or account owner about upgrading if needed

Powered by Plain