# Pricing - Lean Models

The runtime is free. Models are one-time purchases - buy once, run forever on your hardware.

## Free

- Lean runtime (single binary, all platforms)
- lean-agent-35b (35B MoE, 3B active)
- lean-coder-80b (80B MoE, 3B active)
- All quantization variants
- OpenAI-compatible API server

## Paid Models

One-time purchase. No subscription, no recurring fees, no expiration.

| Model | Q4 Size | Min VRAM | Price |
|-------|---------|----------|-------|
| lean-agent-122b (122B MoE, 10B active) | 75.0 GB | 24 GB | Coming soon |
| lean-reason-397b (397B MoE, 17B active) | 244.1 GB | 48 GB | Coming soon |
| lean-think-398b (398B afmoe, ~13B active) | 241.9 GB | 48 GB | Coming soon |
| Full catalog bundle | - | - | Coming soon |

Free updates to purchased models forever.

## Every model includes

- Model weights in `.lmpack` format with expert activation profiles
- Multiple quantization variants (quality, balanced, compact)
- Download via `lean pull`
- Free updates forever
- Commercial use - no restrictions on deployment