https://mecanik.dev/en/tags/kimi-k3/Recent content in Kimi K3 on [ MECANIK DEV ]Hugo -- gohugo.ioenCopyright © 2020-{year} by [ MECANIK DEV ]. All Rights Reserved.Wed, 05 Aug 2026 19:00:00 +0100https://mecanik.dev/en/posts/self-hosting-kimi-k3-hardware-cost/Wed, 05 Aug 2026 19:00:00 +0100https://mecanik.dev/en/posts/self-hosting-kimi-k3-hardware-cost/Self-hosting Kimi K3 became technically possible on 27 July 2026, when Moonshot AI published the weights for a 2.8-trillion-parameter model alongside production inference support. A great many organisations read that news and concluded they could now run frontier-class reasoning on their own hardware and stop paying per token. That conclusion is usually wrong, but not for the reason people expect. The engineering is achievable. The arithmetic is what defeats most projects, and it defeats them quietly, several months after the budget was approved.https://mecanik.dev/en/posts/kimi-k3-api-pricing-integration/Wed, 05 Aug 2026 07:00:00 +0100https://mecanik.dev/en/posts/kimi-k3-api-pricing-integration/The Kimi K3 API arrived with an unusual combination behind it: frontier-adjacent benchmark results, aggressive pricing, and downloadable weights. Moonshot AI published those weights on 27 July 2026, which makes K3 the largest openly available model released so far and the first time a model at this scale has been something you could, in principle, run yourself. For anyone already paying a frontier provider, that raises a practical question rather than a philosophical one.