mirror of
https://github.com/hanzo-docs/docs.git
synced 2026-10-25 04:20:02 +00:00
zeekay
c28fad9afc
Two independent defects made every documented 'first API call' fail: 1. FICTIONAL MODEL IDS. `zen-omni` and `zen-coder` appear ZERO times in the live catalog (api.hanzo.ai/v1/models, 440 models). Every SDK sample - python, typescript, go, cpp, swift, kotlin - told the customer to call a model that does not exist, so even a correct request 400s. Corrected to the real ids: zen5 and zen5-coder. 2. DEAD HOST + STALE PINNED MODEL. llm.hanzo.ai is retired and 301s (a POST returns the literal string 'Permanent Redirect', not a completion), and `claude-sonnet-4-5-20250929` is long superseded. Both removed: the host is gone from customer-facing docs entirely rather than documented as retired, and pinned upstream ids give way to our own current zen5. 50 files. Verified against the live catalog, not assumed.
Zen LM Documentation
Documentation site for Zen LM - frontier AI models for code, reasoning, and multimodal understanding.
Built with Hanzo Docs.
Development
# Install dependencies
pnpm install
# Start dev server
pnpm dev
# Build for production
pnpm build
Structure
docs/
├── app/ # Next.js app directory
│ ├── (home)/ # Landing page
│ ├── docs/ # Documentation pages
│ └── api/ # API routes
├── content/docs/ # MDX content
│ ├── index.mdx # Introduction
│ ├── getting-started/ # Quickstart guides
│ ├── models/ # Model documentation
│ └── training/ # Training guides
├── lib/ # Utilities
└── source.config.ts # MDX configuration
Models
- zen4-max - 1.04T MoE, 256K context
- zen4 - ~400B Dense flagship
- zen4-coder - 480B MoE code specialist
- zen4-coder-flash - Fast code generation
- zen3-omni - ~200B multimodal
- zen3-nano - 4B edge deployment