Models and reasoning effort
The Codexe models (Lite, Pro, Max), which plan each needs, defaults, reasoning effort levels, relative costs and output limits.
Updated
On this page
Codexe runs its own line of models. You choose one per project (on Create or in Project settings), and your plan decides which ones you can pick.
#Available models
| Model | Minimum plan | Good for | Relative cost |
|---|---|---|---|
| Codexe Lite (default on Free) | Free | Small plugins, scripts, quick edits | 1× |
| Codexe Pro (default on paid plans) | Pro | Full plugins, mods and bots | 2× |
| Codexe Max | Business | Large multi-file projects, our strongest model | 4× |
"Relative cost" is how many tokens a model uses for the same work compared with Codexe Lite. The pricing page always shows the current list and multipliers, and the model picker only offers what your plan includes.
#Choosing a model
- Small plugins, scripts, edits: Codexe Lite is fast and cheap.
- Complete plugins, mods, Discord bots: Codexe Pro reasons more and gets more right the first time.
- Large multi-file projects and tricky APIs: Codexe Max, on Business.
- Web search works with Codexe Lite and Codexe Pro, on Business and Enterprise. Codexe Max doesn't search. See Web search.
Every project, whatever the model, goes through the same build check: Codexe compiles it and repairs what fails before handing it over.
#Reasoning effort
Reasoning effort is how much the model thinks before answering. Choosing it is a Pro feature; Free accounts run at the lowest setting.
| Model | Levels you can choose |
|---|---|
| Codexe Lite | Low, Medium |
| Codexe Pro | Low, Medium, High |
| Codexe Max | Low to Extra High |
Low and Medium cost the same. High, Extra High and Max cost progressively more tokens per request. They're worth it for complex, multi-file work and wasted on a one-line change.
#Output limits
On the Free plan a single reply can be at most 4,000 output tokens. A project's first generation is allowed up to 16,000 so the whole project fits, and Codexe pays for the part above 4,000 itself. Paid plans have no per-reply cap beyond the model's own limit.
#Projects made with older models
Until September 2026 Codexe offered models from several providers by name. Every project that used one of them now runs on the Codexe model of the same plan level: the cheaper ones on Codexe Lite, the mid-range ones on Codexe Pro, the top ones on Codexe Max. You don't need to do anything.