Power user

Pick the right AI model and thinking level

After this you'll be able to:

switch model and thinking level in any big app
save your limits for the jobs that need it
test two models on your own task

The rule of thumb

Leave everyday questions on the default or Auto. Turn the model or thinking level up for hard or important work: a tricky problem, a long document, a big decision.

Thinking costs more

Higher levels are slower and use your limit faster. Anthropic says Low and Medium effort stretch your limits and High is the best balance. ¹ Google says more advanced models and higher thinking levels use more of your Gemini limit. ² In Grok, usage costs vary by product, all from one weekly pool. ³

Leaderboards help, your test decides

Independent leaderboards rank models, and an older model sometimes beats a newer one. Run your own 3-task test before you pay for a bigger plan. All rankings.

Where is the model setting in each app?

Grok: Mode menu under the message box on grok.com and in the app. Auto (picks Fast or Expert) · Fast (default) · Expert (thinks hard) · Heavy (a team of AI agents)
Claude: Model menu next to the send button; click it, then Effort. Pick a model (Haiku, Sonnet, Opus, Fable on Max and Ultra), then Effort: Low · Medium · High · Extra high · Max (levels vary by model)
Gemini: Tap the model name inside the text box at the bottom (you must be signed in). Auto (default) or pick Flash-Lite · Flash · Pro, then a thinking level: Standard · Extended · Deep Think (AI Ultra only)
ChatGPT: Model menu at the top of the chat; choose GPT-6, then move the Thinking slider. Instant (fast) · Medium · High · Extra High · Pro. Free and Go get Instant plus a Think button
Copilot: Mode menu at the bottom left of the chat box. Smart (default, decides how hard to think) · Think Deeper · Quick response · Study and learn · Search

Prompt: test two models on my task

I'm comparing two AI models. Here's a real task from my week: [paste]. Answer it, then list any assumptions you made and what you're least sure about.

Run the same prompt in a fresh chat on each model and compare the answers side by side. Sources for the settings: Grok⁴ Claude¹ Gemini² ChatGPT⁵ Copilot⁶

Next topic: Get better answers

Pick the right AI model and thinking level

The rule of thumb

Thinking costs more

Leaderboards help, your test decides

Sources (6)

AI moves fast. We'll keep you up to speed.

Pick the right AI model and thinking level

The rule of thumb

Thinking costs more

Leaderboards help, your test decides

Sources (6)

Prices change often. Get the changes by email.