Pro Tip: Use ChatGPT's Model Picker Before the Prompt

OpenAI simplified the ChatGPT model picker on June 10, 2026 so Plus and Pro users can choose reasoning levels from the composer. The important habit is simple: choose the model behavior in the interface before you write the prompt.

Do not spend prompt tokens telling ChatGPT to "use high reasoning" when the interface already gives you the control. Pick the right mode first, then use the prompt to define the work.

That is the whole pro tip. The model picker is a workflow control. The prompt is an instruction set. Do not make one do the other's job.

The better habit

Use Instant for routine drafting, summaries, rewrite passes, and low-risk questions. Use higher reasoning when the decision has cost, timing, people, customer, compliance, or reputational consequences.

Then prompt for the actual decision structure.

Here is the cleaned-up version:

Act as a decision editor for an Executive. Decision: [DECISION] Context: [FACTS] Constraints: [BUDGET, TIME, PEOPLE, RISK, CUSTOMER IMPACT] Options: [A/B/C] Success looks like: [SUCCESS CRITERIA] If one missing fact would materially change your answer, ask for it first. Otherwise, state your assumptions and proceed. Compare the options in a table with upside, downside, hidden assumption, failure mode, and best-case use. Then give: 1. recommended option, 2. strongest argument against it, 3. what would make you reverse the call, 4. first action in the next 24 hours, and 5. owner plus check-in metric.

Why this prompt is stronger

It does not waste words restating the model mode. It spends those words on decision quality.

The role gives the model a clear posture: decision editor, not motivational coach.

The context fields keep the answer grounded in your facts.

The constraints force tradeoffs into the answer.

The success criteria tell the model what good means before it starts optimizing.

The missing-fact gate prevents false certainty. If the model needs one fact that would materially change the answer, it should ask for it before drafting a confident memo.

The table makes the comparison inspectable. Upside, downside, hidden assumption, failure mode, and best-case use are hard to hide behind.

The final five outputs turn the response into a usable memo: recommendation, objection, reversal trigger, next action, and owner.

How to choose the mode

Use a simple rule: the more expensive the mistake, the more reasoning you buy.

Instant is fine for drafts, summaries, rewrites, brainstorming, and low-risk first passes. It is also useful when you need speed and the decision is reversible. If the answer is wrong, you can cheaply correct it.

Use a higher reasoning mode when the decision has meaningful downside. That includes vendor commitments, hiring decisions, budget reallocations, customer escalations, pricing changes, public messaging, and anything that creates cleanup for another team.

Do not make this mystical. The model picker is just a cost and attention control. You are deciding whether the task deserves more deliberate analysis.

Here is the internal shorthand:

• Instant: "Help me get started."
• Medium or High: "Help me think through tradeoffs."
• Extra High or Pro: "Help me inspect a consequential decision before I act."

The prompt stays the same. The mode changes the depth of the reasoning. That makes the comparison fair and teaches your team what level of model effort a task deserves.

Avoid the token-wasting version

The weak version of this prompt starts with instructions like "use deep reasoning" or "think very carefully." That is not the best use of the prompt. If the interface lets you choose the reasoning level, choose it there.

Spend the prompt on facts, constraints, success criteria, and review requirements. The more clearly you define the decision, the less the model has to guess. The less it guesses, the more useful the output becomes.

Run the two-mode comparison

For one important decision, run the same prompt twice:

• Once in Instant.
• Once in a higher reasoning mode.

Do not compare which answer is longer. Compare which answer is easier to trust after review.

Use this scoring pass:

Score both answers from 1 to 5 on constraint awareness, quality of tradeoffs, clarity of recommendation, usefulness of the strongest objection, and practicality of the next action. Then explain which answer I should use and what to borrow from the other one.

That comparison teaches your team when the model picker matters. It also keeps people from using the heaviest mode for every tiny task.

Save it as a template

Turn the winning version into a reusable decision memo template. Use it for:

• Vendor selection.
• Hiring priority.
• Budget allocation.
• Product sequencing.
• Customer escalation plans.
• Go or no-go calls.

The point is not to outsource judgment. The point is to stop letting important decisions sit in messy notes and private intuition.

Action steps

• Pick the model mode in ChatGPT before writing the prompt.
• Run one real decision through the template in Instant and a higher reasoning mode.
• Save the better output as a one-page memo and use the scoring pass to decide which mode deserves the next run.

Source: https://help.openai.com/en/articles/6825453-chatgpt-release-notes