Self-hosting Kimi K3 (2.8T) in 2026: GPU sizing, cost, and the API break-even
Kimi K3's API costs $3/$15 per million tokens. Self-hosting the 2.8T open weights needs roughly 1.4 TB of VRAM. We size the GPUs, price the node against 2026 cloud rates, and work out the break-even.
