Choosing an AI Model
Every model-enabled feature starts on Auto, so you do not need to understand model names to get a strong result. You can still open the model picker and choose a named model whenever you want more control.
Default model by plan and feature
Reasoning effort describes how long the automatic model is allowed to think, review, and improve its answer or creation. Low prioritizes efficiency, Medium adds more deliberation, and High gives the model the most time for complex work.
| Feature | Free | Premium | Laureate Auto |
|---|---|---|---|
| AI Chat | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna High reasoning | Frontier Boost on: Claude Opus 5; off: GPT 5.6 Luna Opus: Low · Luna: High |
| Deep Research | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna High reasoning | Frontier Boost on: Claude Opus 5; off: GPT 5.6 Luna Opus: Low · Luna: High |
| AI Slides and document creators: PDF Documents, Study Guides, Worksheets, Timelines, SOPs, Flowcharts, Lesson Plans, Outlines, Cheat Sheets, Reports, Case Studies, Rubrics, Spreadsheets, File Documents, and Essay Writer | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna High reasoning | Frontier Boost on: Claude Opus 5; off: GPT 5.6 Luna Opus: Low · Luna: High |
| AI Video Lectures | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna High reasoning | Frontier Boost on: Claude Opus 5; off: GPT 5.6 Luna Opus: Low · Luna: High |
| Infographics and Mind Maps | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna High reasoning | Frontier Boost on: Claude Opus 5; off: GPT 5.6 Luna Opus: Low · Luna: High |
| Flashcards | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna Medium reasoning | GPT 5.6 Luna High reasoning · Never uses a Frontier Boost |
| Podcasts | GPT 5.6 Luna Low reasoning | GPT 5.6 Luna High reasoning | Frontier Boost on: Claude Opus 5; off: GPT 5.6 Luna Opus: Low · Luna: High |
The AI Image Playground uses a separate image-model catalog: Nano Banana 2 Lite is its default on Free, Premium, and Laureate. Text reasoning effort does not apply. Voice Mode also uses a separate real-time voice system.
What is a Frontier Boost?
A Frontier Boost switches Auto (Laureate) from GPT 5.6 Luna to Claude Opus 5. Laureate includes:
- 20 creation Frontier Boosts each week within its 75 total weekly creations.
- 20 Chat Frontier Boosts each week, separate from creation usage.
Turn Frontier Boost on to use Opus or off to use GPT 5.6 Luna at high reasoning. When the relevant boosts run out, Auto keeps working with Luna. Chat remains unlimited and the rest of the 75-creation allowance remains available. Flashcards always use Luna at high reasoning and never spend a boost.
A failed creation or Chat response automatically returns any boost it reserved. All three weekly allowances reset every Monday at 00:00 UTC.
Where you can pick a model
Model selection is available in:
- Home and AI Chat
- AI Slides and document creators
- Deep Research
- AI Video Lectures
- Podcasts
- Flashcards on paid plans
- Worksheets, Study Guides, Mind Maps, and Infographics on paid plans
The picker shows Auto, Auto (Premium), and Auto (Laureate) on every plan so the plan differences are visible before upgrading. Named choices are organized into Recommended Models, Frontier Models, and More Models. Inaccessible rows open the relevant upgrade offer. The Frontier Boost control sits with the other model controls at the bottom of the picker. AI Chat remembers your selection across sessions; creation tools start from the Auto row for your current plan each time.
For Chat and most creation tools, Premium's Recommended Models are GPT 5.6 Terra, Grok 4.6, Claude Sonnet 5, and Gemini 3.1 Pro Preview. Flashcards use a focused recommendation: GPT 5.6 Luna. Free users can browse these paid choices, but selecting one opens the Premium offer.
Models marked Frontier are the most capable, higher-compute choices. Premium includes the recommended Grok, Sonnet, and Gemini Pro models without requiring a Laureate Frontier Boost. Other locked Frontier models open the Laureate offer. Eligible Enterprise workspaces use the same Frontier badge under their workspace model policy instead of individual Frontier Boosts.
Named models
The exact catalog changes as models are released or retired. Current choices across features include GPT 5.6 Sol, Terra, and Luna; Gemini 2.5 Flash, 3 Flash, 3.5 Flash Lite, 3.6 Flash, and 3.1 Pro Preview; Grok 4.6; Deepseek Flash; Mistral Small, Medium, and Large; and Claude Haiku 4.5, Sonnet 5, and Opus 5.
On Laureate, selecting a named Frontier model directly uses the same relevant weekly boost allowance. Selecting an unbadged model does not use a boost. If no boost remains, leave the picker on Auto to continue with Luna at high reasoning.
Thinking in Chat
Some named Chat models offer a Thinking control. Turning it on lets the model reason before answering and shows a progress summary that collapses into a completed thought block. Other models always reason and do not show the control.
For Auto (Laureate), Frontier Boost on uses Opus at low reasoning and Frontier Boost off uses Luna at high reasoning.
Model data handling and privacy
Scholarly never sells your content or uses your prompts and sources to train AI models. Your material is sent only to the provider needed to produce your requested result. See the Privacy Policy for full details.
Tips
- If you are unsure, leave the picker on Auto.
- Try another named model when you want a different writing style or a second take.
- For Laureate, turn Frontier Boost on when you want Auto to use Opus and off when you want Auto to use Luna.
- Every completed creation still uses one creation from the plan's main allowance, regardless of model.