Creating a project
Everything on the Create page, including project types, models, reasoning effort, attachments, ZIP import, the Enhance button and the cost estimate.
Updated
On this page
Every project starts on Create. This page walks through each part of it.
#Project type
The type picker groups every supported target:
| Group | Types |
|---|---|
| Minecraft · Plugins | Bukkit/Spigot/Paper (Java), Bukkit/Spigot/Paper (Kotlin), Folia, BungeeCord/Velocity |
| Minecraft · Mods | Forge, Fabric |
| Minecraft · Datapacks / Skripts | Datapack, Skript |
| Minecraft · 3D Models | Blockbench model (alpha) |
| Discord | Discord bot (Python), Discord bot (Node.js) |
| Website | Static website (HTML/CSS/JS), React application |
The type controls the project scaffold, the build tool and how Codexe verifies the result. If your request clearly describes a different type ("a Fabric mod that…" while Spigot is selected), Codexe switches the type and shows a notice so you can switch back.
#The request box
Write what you want. How to write a good request covers what to include. There's no separate Minecraft-version selector: write the version in the request ("Paper 1.21.4", "Fabric 1.20.1"), and Codexe picks the matching Java version for the build.
#Model and reasoning effort
The default model is chosen for your plan. Paid plans can pick other models and a reasoning effort (how much the model thinks before answering; higher effort costs more). Free accounts use the default effort. See Models.
#Attachments
Use +, paste or drag and drop to attach reference files (existing code, config files, screenshots). Per-file limits:
| Plan | Code / text file | Image |
|---|---|---|
| Free | 150 KB | 2 MB |
| Pro | 750 KB | 8 MB |
| Business | 1.5 MB | 20 MB |
| Enterprise | 2 MB | 50 MB |
To start from an existing project, see Importing a project.
#Enhance
Enhance rewrites your request into a more complete specification using a fast model. It costs a flat 5,000 tokens. Read the result before generating: it may add assumptions.
#Cost estimate
Before you generate, Create shows an estimate of the tokens the request will use. The final cost is settled against what the model actually used, so it can end up a little higher or lower. See Credits.
#One generation at a time
Each account runs one generation at a time. If another of your projects is still generating, wait for it to finish. There are also fair-use limits on how many generations you can start per hour (30 per hour, fewer on the most expensive models and highest reasoning efforts).