Models & Premium Requests
Choosing a Model
The first thing to know about is the model picker at the bottom of the chat window. This defaults to Auto, which means Copilot will just choose a model for you — that's totally fine and comes with a small cost discount.
But if you want to choose manually, you can click the model picker and select from models made by Anthropic (Claude), OpenAI (GPT/Codex), Google (Gemini), xAI (Grok), and others. The lineup changes over time, so just know the options will vary.
Pricing
A quick note on cost. Most Copilot plans come with a set number of premium requests per billing period. Each model has a multiplier that determines how many premium requests each message uses:
Free models — unlimited, doesn't touch your budget
1x models — one premium request per message
Fractional models — cheaper than one request per message
Higher-end models — can be 3x, 7x, even 10x per message
The multiplier is a decent signal for how capable the model is. More expensive usually means more powerful. You can check your usage by clicking the Copilot icon at the bottom of the chat.
If you use up all of your premium requests, you can “pay as you go” for more. As of April 27, 2026, additional requests are $0.04 per request.
Thinking Effort
Some models also have a thinking effort toggle (low/medium / high), which controls how much reasoning the model does before responding.
A good starting point is just a 1x model or Auto. We can get into strategy around model selection as we go. Generally, thinking effort will affect how long the model takes to complete a task, a good default is High if you’re unsure.
✏️ Explore the models
Take a minute to explore the model picker and view your current usage.
Open the model picker and choose 2 models to use for the remainder of the training, one
1xmodel and one cheaper/faster one (0.33xor0x).
Practice switching between
Thinking EffortmodesTry to match each model with its provider (OpenAI, Anthropic, Google, xAI
Make a note of your current usage and remaining premium requests.
Next: Ask Mode