Moonshot AI

Latest AI news, models and releases from Moonshot AI. ['GLM 5.2', 'GLM-5.2', 'Hermes', 'K2', 'K2.6', 'K2.7', 'K3', 'K3-mini', 'K3-MoE', 'Kimi', 'Kimi 2.6', 'Kimi-2.6', 'Kimi 3', 'Kimi 3T', 'Kimi Hosted Agent', 'Kimi k1.5', 'Kimi K1.5', 'kimi-k2', 'Kimi K2', 'kimi-k2-0711-preview', 'Kimi K2.5', 'Kimi-K2.5-1T-A32B', 'Kimi K2.6', 'Kimi K2.7', 'Kimi K2.7 Code', 'Kimi K2 Thinking', 'Kimi K3', 'Kimi-K3', 'Kimi K3.5', 'Kimi-k3-free', 'Kimi K4', 'Kimi K5', 'Kimi Linear', 'Kivine', 'Krea 2', 'Krea 2 Turbo', 'Mamba', 'Mamba-2', 'Mamba-3', 'MiniCPM-RobotManip']

Self-hosting vs API: how to calculate the real cost of a solved task in the era of open models

The article argues that comparing self-hosting and API based on per-token prices is misleading. It proposes using blended API prices and total cost of ownership for self-hosting, with a break-even volume dependent on utilization. For solved tasks, it introduces a cost-per-task metric incorporating model solve rates and token budgets, highlighting that cheap API often beats self-hosting for the same model due to provider scale.

Moonshot AIMoonshot AI DeepSeekDeepSeek AnthropicAnthropic
Habr — хаб ИИ26.07 · 23:02
Fresh news