Choosing an AI Model

Scholarly lets you choose which AI model powers your conversations, slide decks, and video lectures. Different models have different strengths -- swapping between them is a good habit when one output does not quite hit the mark.

Where You Can Pick a Model

You can pick an AI model in several places:

• Home chat box -- The model picker now sits right next to the Home chat input, so you can swap models before sending your first message — no need to open a chat first.
• AI Chat -- Open the model menu above the chat input to switch models for a new or existing conversation.
• AI Slides -- Pick a model in the slide creator before you click Generate.
• Deep Research -- Pick a model above the research chat input before you run a session. Gemini 3.5 Flash Lite is the low-reasoning default on every plan.
• AI Video Lectures -- Gemini 3 Flash is the low-reasoning default on every plan, including Free. Paid users can pick another model in the video creator before they click Generate.
• Flashcards (paid plans) -- Pick which model writes the deck in the customize step of the flashcard creator. Gemini 2.5 Flash is the default on every plan, and Gemini 3 Flash is the alternative.
• Worksheets, Study Guides, Mind Maps, Infographics (paid plans) -- Pick a model in each create modal before generating. Free users see the option with a lock badge.

Each provider's logo (OpenAI, Google, xAI, Mistral, or Anthropic) shows next to its models in the picker so you can tell families apart at a glance. AI Chat remembers your selected model across sessions. The Deep Research and artifact-generation pickers listed above apply a model choice only to the current creation and start from their default again the next time you open them.

Recommended Models and Other Models

Every model picker — in chat and in every AI create tool — is organized into two groups. A short Recommended Models list sits at the top with the best picks for that feature, and everything else lives in an Other Models submenu one tap away. Each model has a short, plain-English description underneath ("fast and lightweight", "clear, well-paced lectures") so you can tell at a glance what each one is good for without having to memorize names.

Each creation tool starts on its plan-appropriate default. AI Video Lectures use Gemini 3 Flash at low reasoning effort on every plan, Flashcards use Gemini 2.5 Flash, and the other model-enabled creation surfaces use Gemini 3.5 Flash Lite at low reasoning. Paid users can open Other Models when they want a different style.

Browsing the Picker on Free

Free users can open the model picker and browse every Free and Ultimate model, with the same Recommended badge and descriptions paid users see. You can read about each model before deciding whether to upgrade. Actually choosing a non-default model stays part of the paid plan. Enterprise-only models are shown only inside Enterprise workspaces.

Available Models

The exact list updates as new models are released. Common options include:

• GPT 5.6 Sol (Enterprise) -- OpenAI's premium flagship in Scholarly. Pick it for the hardest reasoning, careful source work, and polished long-form output.
• GPT 5.6 Terra -- A balanced paid option for everyday questions, explanations, and grounded study help.
• GPT 5.6 Luna -- The default chat model on every plan for quick answers and high-volume work with lower cost and latency. Paid users can turn on Thinking for harder prompts.
• Gemini 3.5 Flash Lite -- Google's fast, efficient low-reasoning default for Deep Research, AI Slides, and infographics on every plan. It remains an optional chat and paid AI Video Lecture model.
• Gemini 2.5 Flash -- Google's reliable, cost-efficient flashcard default on every plan.
• Gemini 3.1 Pro Preview -- Google's newest premium reasoning model for chat. A strong pick for careful explanations, long-context source work, and problems where you want thinking built in.
• Gemini 3.6 Flash -- Google's premium reasoning model for chat and supported creation workflows, including AI Video Lectures. A strong pick when you want careful explanations, long-form analysis, or source-heavy work.
• Gemini 3 Flash -- Fast, capable, and efficient. The low-reasoning default for AI Video Lectures on every plan and an optional model for AI Chat, AI Slides, Deep Research, infographics, and flashcards. In AI Chat, reasoning is always on.
• Grok 4.5 -- An optional premium model for AI Chat, AI Slides, Infographics, Research, and AI Video Lectures. It is creative, confident, and effective at multi-step work. In AI Chat, thinking is always on (no Instant / no-thinking mode).
• Mistral Small 4 -- A fast European model from Mistral AI with a large context window and optional thinking mode. It is available in AI Chat for quick everyday questions.
• Mistral Medium 3.5 -- Mistral's stronger reasoning model for paid chat. Use it for complex explanations, multi-step work, and source-heavy questions.
• Mistral Large 3 -- Mistral's larger premium chat model. A good alternate when you want a careful Mistral answer without turning on thinking.
• Claude Sonnet 5 -- Anthropic's newest Sonnet model. It is available on paid plans for AI Video Lectures and reserved for Enterprise on AI Chat, Deep Research, AI Slides, and infographics. Pick it for long-document analysis, careful reasoning, visual source understanding, and nuanced explanations.
• Claude Haiku 4.5 -- Anthropic's fast everyday model. Lighter and quicker than Sonnet, still strong at writing and reasoning. Good default when you want Claude's style without waiting.

Locked Models on the Free Plan

Some models require a paid plan. When premium choices are shown on the Free plan, they use a small lock badge so you know what an upgrade unlocks. Selecting a locked model prompts you to upgrade rather than switching to it.

Free models stay fully available without a lock badge. Ultimate unlocks the paid individual-plan catalog. GPT 5.6 Sol remains reserved for Enterprise, while Claude Sonnet 5 is available on paid plans for AI Video Lectures and reserved for Enterprise on its other supported surfaces. See Plans and Limits.

You can still browse every model — including locked ones — to compare. The picker doesn't hide anything from you.

How to Pick

A few simple heuristics:

• Making a video lecture? Start with Gemini 3 Flash — it is the efficient low-reasoning default on every plan.
• Need a quick answer or outline? Start with the default GPT 5.6 Luna.
• Need deep reasoning or step-by-step math? Try Gemini 3.1 Pro Preview, Gemini 3.6 Flash, or a reasoning-enabled GPT model.
• Want creative phrasing or brainstorming? Try Grok 4.5 or Mistral Small 4.
• Reading a long PDF or working through a careful explanation? On Enterprise, try Claude Sonnet 5 -- it handles long documents and nuanced reasoning especially well.
• Want a European model family? Try Mistral Medium 3.5 for reasoning or Mistral Large 3 for a premium non-thinking pass.
• Want Claude's writing style without the wait? Try Claude Haiku 4.5 -- fast, lightweight, still thoughtful.
• Not sure? Start with GPT 5.6 Luna on any plan. Paid users can turn on Thinking or choose GPT 5.6 Terra for stronger OpenAI reasoning; Enterprise workspaces can choose GPT 5.6 Sol for the strongest OpenAI reasoning.

If the first result does not feel right, regenerate with a different model. Slide decks and video lectures are quick to re-run, and each model gives a noticeably different style.

Thinking Toggle (Chat Only)

In AI Chat, you can enable a Thinking toggle in the model menu. When turned on, the model reasons through the problem before replying -- which produces better answers for complex questions, math, and multi-step problems.

• Off -- Fastest responses, no visible reasoning step.
• On -- The model thinks before answering. You see a live progress summary while it reasons, which collapses into a "Thought for X seconds" block when done.

Not every model supports thinking. Some models always reason and do not show the toggle because thinking is built in. Gemini 3.5 Flash Lite, Gemini 3 Flash, Gemini 3.1 Pro Preview, and Grok 4.5 always reason in chat. Both Claude models support the Thinking toggle -- it is especially useful on Claude Sonnet 5 for hard, multi-step problems. Mistral Small 4 and Mistral Medium 3.5 also support thinking mode; Mistral Large 3 appears as an instant-response premium option.

Model Data Handling and Privacy

Scholarly never sells your content and never uses your prompts or sources to train AI models. Your material is used only to generate the result you asked for.

The models are run through their AI providers (OpenAI, Google, Anthropic, xAI, and OpenRouter for Mistral chat models). A few of the most advanced, top-tier models carry extra provider requirements: the provider may hold the request for a short period (typically up to 30 days) for safety and abuse monitoring before deleting it, and may occasionally decline a request that trips its safety systems. The standard models don't carry these requirements — so if you'd prefer to avoid any provider-side retention, pick one of them.

For the full details on how Scholarly handles your data, see the Privacy Policy.

Tips

• Experiment! The fastest way to find your favorite is to generate the same slide deck or short lecture with two different models and compare.
• Some chat models require a paid plan — those show a lock badge in the picker on the Free plan. Model choices inside AI Slides and AI Video Lectures follow those features' normal plan limits.
• For creative or exploratory work, a different model can unlock a completely different angle on the same source material.