# Using the AI chat and choosing a model

> How messages are processed, how edits work, and which models you can choose on each plan.


## How a message runs

Each message is one job: the AI thinks, writes files, Draftship builds the app, and fixes the build if needed. One job runs per project at a time; Pro+ can run jobs in three projects at once and is served first when the platform is busy.

## Edits only touch what changes

When you ask for a change, Draftship sends the current files and your request, and the AI returns only the files it needs to create or modify. That keeps edits quick and reduces accidental changes elsewhere.

## Models

| Model | Plan | Best for |
|---|---|---|
| **Draftship AI** | All plans | Our default — bold, polished designs. |
| Claude Haiku 5.5 | Pro | Speed and clean code. |
| Kimi K2.7 Code | Pro | Coding-heavy apps. |
| Gemini 3.8 Flash | Pro | Multi-page layouts. |
| Claude Sonnet 5.5 *(premium)* | Pro | Highest quality; uses limits much faster. |
| Claude Opus 5.5 *(premium)* | Pro+ | The most capable model. |

Pick a model in the prompt box or the chat box. Set your default in **Settings → Models**. The picker shows roughly how much of your weekly limit a new app uses with each model.