AI models
Frontier models, assigned per surface.
Run a reasoning model where depth wins and a fast one where a three-second pause reads as hesitation. Same session, no restart.
Per-surface selection
Chat, coding, and system design each get their own model. Set them once in the interview setup.
Reasoning where it counts
System design rewards a model that thinks. Assign GPT-5.4 or Claude Opus 4.6 to that surface alone.
Speed where it shows
In a behavioral round, latency is visible. Keep something fast on chat so you are never caught waiting.
No API keys to manage
Model access is handled server-side. You never paste a key into the app or babysit a billing dashboard.
Catalog
Every model in the app
Frontier models require a Pro or Pro+ plan. Fast models are available on every plan, including Free.
| Model | Provider | Class | Best for |
|---|---|---|---|
GPT-5.4 | OpenAI | Reasoning | System design and complex technical reasoning |
GPT-5.4 Mini | OpenAI | Fast | Fast behavioral answers where latency shows |
GPT-5.3 Codex | OpenAI | Coding | Live coding rounds and algorithm problems |
GPT-5.3 Chat | OpenAI | Fast | Natural conversational phrasing |
GPT-5.2 | OpenAI | Fast | A balanced general-purpose fallback |
GPT-4.1 Mini | OpenAI | Fast | Lowest latency, lightest credit cost |
Claude Opus 4.6 | Anthropic | Reasoning | Deep architecture reasoning and nuanced tradeoffs |
Claude Sonnet 4.6 | Anthropic | Coding | Strong all-rounder for coding and behavioral |
Gemini 2.5 ProSoon | Reasoning | — | |
Grok 3Soon | xAI | Fast | — |
A pairing that works well
Behavioral answers land fastest when they land immediately.
Purpose-built for code; strongest on algorithm rounds.
The extra seconds buy you a genuinely better architecture.
Pick your models and start
Fast models on every plan. Frontier models on Pro and Pro+.