AI models
Frontier models, one for each interview type.
Free is five low-price OpenAI models. Pro and Pro+ add Claude, Grok, and the rest.
URHIRED AI calls models through its own backend, so the desktop app never holds an API key. The free plan includes GPT-6 Luna, GPT-5.6 Luna, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-4.1 Mini. Pro and Pro+ add Claude, Grok, and the other OpenAI models. Assign one model per interview type in Settings.
Pick a model per type
Verbal, coding, system design, and project each get their own model. Set them once in Settings → General.
Reasoning where it counts
System design rewards a model that thinks. Assign GPT-6 Astra or Claude Opus 5.5 to that interview type.
Speed where it shows
In a behavioral round, latency is visible. Keep something fast on verbal 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
Free includes the low-price OpenAI models: GPT-6 Luna, GPT-5.6 Luna, GPT-5.4 Mini, GPT-5.4 Nano, and GPT-4.1 Mini. Claude, Grok, and the other OpenAI models need Pro or Pro+.
| Model | Provider | Class | Plan | Best for |
|---|---|---|---|---|
| GPT-6 Astra | OpenAI | Reasoning | Pro | Frontier reasoning for the hardest architecture rounds |
| GPT-6 Sol | OpenAI | Coding | Pro | Balanced coding and system design at the current flagship |
| GPT-6 Luna | OpenAI | Fast | Free | High-volume speed at the lightest GPT-6 cost |
| GPT-5.6 Sol | OpenAI | Reasoning | Pro | Frontier-depth reasoning for the hardest rounds |
| GPT-5.6 Terra | OpenAI | Fast | Pro | Balanced depth and latency for everyday rounds |
| GPT-5.6 Luna | OpenAI | Fast | Free | High-volume speed at the lightest 5.6 cost |
| GPT-5.5 | OpenAI | Reasoning | Pro | Deep reasoning across long sessions |
| GPT-5.4 | OpenAI | Reasoning | Pro | System design and complex technical reasoning |
| GPT-5.4 Mini | OpenAI | Fast | Free | Fast behavioral answers where latency shows |
| GPT-5.4 Nano | OpenAI | Fast | Free | The fastest answers at the lightest cost |
| GPT-5.3 Codex | OpenAI | Coding | Pro | Live coding rounds and algorithm problems |
| GPT-5.2 | OpenAI | Fast | Pro | A balanced general-purpose fallback |
| GPT-5.1 | OpenAI | Fast | Pro | A stable older generation, still capable |
| GPT-4.1 Mini | OpenAI | Fast | Free | Lowest latency, lightest credit cost |
| Claude Fable 5.1 | Anthropic | Reasoning | Pro | Long-horizon architecture and agentic reasoning |
| Claude Opus 5.5 | Anthropic | Reasoning | Pro | Deep architecture reasoning and nuanced tradeoffs |
| Claude Sonnet 5.5 | Anthropic | Coding | Pro | Strong all-rounder for coding and behavioral |
| Claude Haiku 4.5 | Anthropic | Fast | Pro | Fastest Claude for verbal rounds |
| Claude Opus 4.6 | Anthropic | Reasoning | Pro | Previous Opus generation, still strong on design |
| Claude Sonnet 4.6 | Anthropic | Coding | Pro | Previous Sonnet generation for live coding |
| Grok 4.7 | xAI | Fast | Pro | Fast coding rounds |
| Grok 4.6 | xAI | Coding | Pro | Coding rounds on the 4.6 generation |
| Grok 4.5 | xAI | Coding | Pro | Coding rounds on the 4.5 generation |
| Grok 4.3 | xAI | Fast | Pro | Fast verbal answers at a lower token cost |
| Grok Build 0.1 | xAI | Coding | Pro | Live coding rounds |
A pairing that works well
On the free plan, GPT-6 Luna is the default for verbal, coding, system design, and project. The pairing below is the Pro upgrade.
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.
Repo Q&A stays on a coding model so it can locate and explain files.
Pick your models and start
Low-price OpenAI models on Free. Claude, Grok, and the other models on Pro and Pro+.