Choosing models
You can assign a different model to each surface. Getting this right is the difference between an answer that lands and one that arrives too late to use.
The per-surface model picker in interview setup, showing separate model dropdowns for chat, coding, and system design.
public/docs/settings/model-picker.pngAvailable models
| Model | Provider | Best for |
|---|---|---|
| GPT-5.4 | OpenAI | System design and complex technical reasoning |
| GPT-5.4 Mini | OpenAI | Fast behavioral answers where latency is visible |
| GPT-5.3 Codex | OpenAI | Live coding rounds and algorithm problems |
| GPT-5.3 Chat | OpenAI | Natural conversational phrasing |
| GPT-5.2 | OpenAI | A balanced general-purpose option |
| GPT-4.1 Mini | OpenAI | Lowest latency and lightest credit cost |
| Claude Opus 4.6 | Anthropic | Deep architecture reasoning and nuanced tradeoffs |
| Claude Sonnet 4.6 | Anthropic | A strong all-rounder for coding and behavioral |
Gemini 2.5 Pro and Grok 3 are listed in the picker as coming soon and cannot be selected yet.
A pairing that works
| Surface | Model | Why |
|---|---|---|
| ⌘1 | GPT-5.4 Mini | In a behavioral round, a three-second pause reads as hesitation. Speed wins. |
| ⌘2 | GPT-5.3 Codex | Purpose-built for code; strongest on algorithm problems. |
| ⌘3 | Claude Opus 4.6 | Design rounds reward depth, and you have time to think anyway. |
The tradeoff to think about
Reasoning models produce better answers and take longer to produce them. That cost is invisible in a system design round, where you are meant to be thinking, and very visible in a rapid behavioral exchange. Match the model to the pace of the round, not to a general idea of which is "best".
API keys
You do not need one. Model access is handled server-side through your account — there is no key to paste into the app and no separate provider billing to manage.