---
title: "Choose which model Kai uses"
description: "On current plans Gleap picks Kai Support's model. Where you can choose (older plans, custom agents on Pro): Auto, pinning a model, and cost per conversation."
url: https://help.gleap.ai/en/articles/239-choose-which-model-kai-uses
collection: "Kai Support"
updated: 2026-11-16
language: en
---

# Choose which model Kai uses

On current plans Gleap picks Kai Support's model. Where you can choose (older plans, custom agents on Pro): Auto, pinning a model, and cost per conversation.

Kai Support's model is set under **AI agents → Kai Support → Settings → Model**. What you see there depends on your plan.

On plans without model selection, **Picked by Gleap** means Gleap chooses the model. Current Kai Support billing follows AI usage. Older workspaces can retain per-resolution or included-AI terms; check **Billing** for the mode your workspace uses. The investigation model is configured separately where your plan allows it.

### Auto is the default

Auto picks a model for the task and falls back to another when one isn't available. That fallback is the main reason to leave it alone: a provider outage doesn't stop Kai from answering.

![Kai support model screen in the Pied Piper demo project.](https://staticfiles.gleap.io/p613b5dd730aed737108f87ab/MISMVkpDcSJDflS3SZq2DKAOIUB784dqonGS45NHPyDwxs2g9WELmGiC215mdyxkhk013XOpknG.png)

On older plans without model selection, the row reads **Auto routing** and can't be changed. The **Unlock** button next to it shows what's needed.

### Pin a specific model

1.  Open **AI agents → Kai Support → Settings → Model**.
    
2.  Open the dropdown. Each entry shows its price per million tokens, input and output.
    
3.  Pick a model. Below the dropdown you see a short description of it and **Cost per conversation**.
    
4.  Compare models by **Cost per conversation**, an estimate for a typical Kai Support conversation, knowledge lookups included. It's closer to what a real conversation costs than the per-million rates.
    

Gleap maintains the list and updates it as models are released and retired. If a model you pinned later leaves the list, your choice keeps working and stays visible in the dropdown, so nothing breaks silently and you can move to a current model when you're ready.

### What changes with the model

-   How the answer reads: phrasing, and how well it holds a longer thread together.
    
-   How it handles a question that needs several pieces of your documentation combined.
    
-   Cost per conversation, which varies widely across the list.
    
-   Whether customers can send screenshots. Not every model reads images. If yours can't, the **Images** switch under Answers & media is disabled and names the model.
    

> **Info:** The model doesn't change what Kai is allowed to say. Answers come from your knowledge sources on every model. A stronger model won't cover a gap in your content, it will only decline more fluently.

### Picking one

Start on Auto and change it only when you have a reason. The usual one is cost, once you can see what you spend per answer. If your customers often send screenshots, check that the model you pin reads images.

After a change, read a handful of real conversations. Model behaviour on your own content is hard to predict from a description, and the difference usually shows on questions your documentation only partly covers.

### Related

-   [How Kai decides what to answer](https://help.gleap.ai/en/articles/235-how-kai-decides-what-to-answer.md)
    
-   [Plans, seats and AI credits](https://help.gleap.ai/en/articles/377-plans-seats-and-ai-credits.md)
    
-   [Kai and your data](https://help.gleap.ai/en/articles/237-kai-and-your-data.md)
