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.

One model per surface, set once in the interview setup.

Available models

ModelProviderBest for
GPT-5.4OpenAISystem design and complex technical reasoning
GPT-5.4 MiniOpenAIFast behavioral answers where latency is visible
GPT-5.3 CodexOpenAILive coding rounds and algorithm problems
GPT-5.3 ChatOpenAINatural conversational phrasing
GPT-5.2OpenAIA balanced general-purpose option
GPT-4.1 MiniOpenAILowest latency and lightest credit cost
Claude Opus 4.6AnthropicDeep architecture reasoning and nuanced tradeoffs
Claude Sonnet 4.6AnthropicA 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

SurfaceModelWhy
⌘1GPT-5.4 MiniIn a behavioral round, a three-second pause reads as hesitation. Speed wins.
⌘2GPT-5.3 CodexPurpose-built for code; strongest on algorithm problems.
⌘3Claude Opus 4.6Design 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.

Frontier models need a paid plan
The free plan includes the fast models. GPT-5.4, GPT-5.3 Codex, Claude Opus 4.6, Claude Sonnet 4.6, and per-surface model selection require Pro or Pro+. Plans & credits →