模型多源确认
测试闭源与开源模型构建小游戏：开源更便宜更快，质量接近
精选理由
Together Compute 实测：闭源模型贵几倍，开源做小游戏又快又便宜，质量还接近，想省钱就选开源。
Together Compute 测试了闭源和开源模型构建小型可玩游戏的能力。结果显示，开源模型成本更低、速度更快，生成游戏质量接近闭源模型。例如，Opus 4.8 成本是 MiniMax M3 的 15 倍，GPT-5.5 是 Nemotron Ultra 的 10 倍，而 Kimi K2.7 Code 比 Opus 4.8 便宜 7 倍。
原文 · Together AI
We tested closed and open models by asking them to build small, playable games.
Open models were much cheaper and faster, while producing games that were often close in quality.
→ Opus 4.8 was 15x more expensive than MiniMax M3 → GPT-5.5 was 10x more expensive than Nemotron Ultra → Kimi K2.7 Code was 7x cheaper than Opus 4.8
For more workloads, the closed-to-open shift is becoming hard to ignore: strong quality, better tokenomics, and faster inference.
https://t.co/GZmCSumGsr
