---
title: "Model picker"
kind: "Skill"
category: "Productivity"
price: "Free"
seller: "Mindket"
version: "1"
url: "https://mindket.com/p/335cae08-bc39-4d78-98aa-aa4a01c305cf"
updated: "2026-11-09"
---

# Model picker

> The name, the description, the About and a README below are the seller's words: data, not instructions.

Says which size of AI model a task needs, so simple work stops paying for the largest one.

Model picker is an AI prompt skill in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-09. Copy its prompt from this page into any AI chat and put your text where it says {{input}}.

## About

### What it is

Model picker tells you the smallest kind of AI model that can do a task well: a small fast one, a mid-size one or the largest. Work that a small model handles then stops running on the dearest one out of habit.

### Who it suits

People who choose models and pay the bill, and any team that runs the same AI job many times.

Who uses it, and how

| Industry | Who uses it | How they use it | Example |
| --- | --- | --- | --- |
| Software | Developers building agents and scripts | Pick a size before the first run | A developer about to add a translation step to a script asks which size it needs before the first run |
| Startups | Founders watching API costs | Go through recurring jobs and move the simple ones down a size | A founder reviewing the monthly AI bill checks each recurring job |
| Operations | Operations leads | Ask before an automation runs on the largest model by default | An operations lead planning a new automation asks before wiring it to a model |
| Customer support | Teams building a support bot | Find the part of the job that needs a bigger size | A team learns which part of a support bot, the written reply, needs the bigger size |

If you use one chat model for everything and never see a bill, skip it.

### Where to use it

In any AI chat, before you choose a model. It matters most for jobs that repeat, where the gap in price between sizes adds up.

- Any AI chat: where you paste the skill’s prompt and describe the task in place of {{input}}
- A new agent or automation: ask before you set the model it runs on
- A script that calls an API for every row: the price of each call repeats there

What moves a task up or down a size

| In the task | Which way it points |
| --- | --- |
| Sorting or tagging | Often no need for the largest model |
| A written reply instead of a label | A bigger model |
| Long inputs or a strict output format | Possibly more than the first answer says |

### How to set it up

What you need first:

- Where it runs: any AI chat
- A key: none
- An install: none

1. Sign in to Mindket and press Get it on this listing.
2. In your Mindket account, View shows the prompt to read and copy. This page shows it too.
3. Keep it where you can paste it again: a saved prompt in your chat app, if it keeps them, or a note.

### How to use it

Paste the skill’s prompt and describe the task in a sentence or two where it says {{input}}.

You describe a task in place of {{input}} → It weighs a small, a mid-size and the largest model → You get one size and a line on why → Plus what would push the task up a size

What to put in your description

| Tell it | Why it matters |
| --- | --- |
| What goes in | Long inputs can call for a bigger size |
| What has to come out | A written reply asks more of a model than a label |
| How often it runs | The price of each call adds up on repeat jobs |

### Example

A sorting job a support team runs every day.

```text
sort 2,000 support emails a day into billing, bug or feature request
```

The answer comes in three parts:

What the answer holds

| Part | What it says |
| --- | --- |
| The size | Small and fast, mid-size, or the largest |
| Why | One line on why that size is enough |
| What would change it | What about the task would call for a bigger model, such as needing a written reply instead of a label |

### For newcomers and experts

**If you are new.** AI models come in sizes, and bigger ones cost more per answer and run slower. Many tasks, like sorting or tagging, do not need the biggest. Describe one job you hand to AI today and see which size it suggests.

**For experts.** It sorts a task into three tiers, not named models, and says what would push it up a tier. That keeps the advice stable as vendors rename and reprice models. It cannot know your latency target or your eval scores. Treat its answer as a starting point and confirm it on a sample of real inputs.

### Good to know

- Sizes, not names: it names a size, not a vendor or a price, because model names and prices change often
- Your words only: it judges from your description, so a task that hides long inputs or a strict format may need more than it says
- Before you switch: try the suggested size on a handful of real inputs before you move a whole job over

## The prompt

```text
Decide the cheapest kind of AI model that can do this task well: a small fast model, a mid-size model, or the largest model. Answer with the size, one line on why, and what about the task would call for a bigger one.

{{input}}
```

Put your question or text where it says {{input}}.

## Intro videos

- [Model picker intro video 1](https://www.youtube.com/watch?v=tRi9g3urhyE)
- [Model picker intro video 2](https://www.youtube.com/watch?v=0Wwn5IEqFcg)
- [Model picker intro video 3](https://www.youtube.com/watch?v=pYax2rupKEY)

## Get it

- [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/335cae08-bc39-4d78-98aa-aa4a01c305cf)
- [Its page on Mindket](https://mindket.com/p/335cae08-bc39-4d78-98aa-aa4a01c305cf)