AI Providers
The built-in Hyper 30 model works out of the box — bring your own keys only if you want to.
HyperDevs ships with Hyper 30, a powerful cloud model for chat, coding, and generation. It's the default and needs no setup — just sign in. If you'd rather use your own account and billing, you can bring keys for Gemini, Claude, OpenAI, or z.ai, or run a local Ollama instance (no key needed), and switch providers per task.
Hyper 30 Built-in · Default
No API key required
- ✓ Works the moment you sign in — nothing to configure
- ✓ Served from the HyperDevs cloud proxy
- ✓ Handles chat, Luau coding, and generation
- ✓ Credit-billed with a free tier (1 credit = $0.01)
Available models: qwen3-35b-worker (default), dynamic
Behind the name: a single 80B Qwen3-Coder-Next MoE served via the HyperDevs cloud proxy — not 30 separate models.
Find it under Settings → AI Providers → Hyper 30. Signing in authenticates your HyperDevs account — this is a HyperDevs cloud credential, not a third-party API key. Power users on the local network can instead point at the direct LAN path and leave the key blank.
Bring Your Own Key
Optional. Add a key under Settings → AI Providers for any of these if you prefer your own account and pricing.
Google Gemini
Affordable & fast
- ✓ Very affordable
- ✓ Fast response times
- ✓ Great quality for coding & creative
- ✓ Easy signup
Available models: gemini-2.5-flash (default), 2.5-pro, 3-flash-preview
Get API Key →Anthropic Claude
Complex coding
- ✓ Excellent for Luau scripting
- ✓ Strong reasoning abilities
- ✓ Long context windows
- ✓ More expensive but worth it
Available models: sonnet-4-5 (default), haiku-4-5, opus-4-5, sonnet-4-20250514
Get API Key →OpenAI
All-around
- ✓ Excellent across all tasks
- ✓ Fast and reliable
- ✓ Great creative capabilities
- ✓ Custom base URL supported
Available models: gpt-4o (default), 4o-mini, 5.4
Get API Key →z.ai (GLM)
Strong & cost-effective
- ✓ GLM-5.2 (default), GLM-5.1, GLM-4.7, GLM-4.6
- ✓ Capable reasoning and coding
- ✓ Competitive pricing
- ✓ Custom base URL supported
Available models: glm-5.2 (default), 4.6, 5.1, 4.7
Get API Key →Local (no key)
Run entirely on your own machine — no account and no API key. Ollama downloads and serves models locally.
Ollama
Free & offline (local)
- ✓ Completely free
- ✓ Runs locally (offline)
- ✓ Run models like gemma4:26b, llama3.2, and more
- ✓ Private — nothing leaves your machine
💡 Tip: Start with Hyper 30 — no key, no setup. Switch to Claude or Gemini for specific coding tasks, or Ollama for fully offline work. See Advanced for local model setup.