Using an open model feels surprisingly good
摘要
作者长期使用 Claude 和 ChatGPT，最近因个人订阅计划不够好，改用 Modal 端点上的 Kimi K3 模型，并用 opencode 连接自己的推理端点。约 5 分钟配置完成，他感到数据只在自己电脑和端点间流动，有种自由和拥有感，像摆脱了其他提供商的束缚，这种体验出乎他意料。
荐读理由
文章确认了 opencode 接 Modal 托管端点跑 Kimi K3 这条路径可行，作者 5 分钟就配好、数据只在本地和端点间流动，你可以照这个思路把推理迁到自己可控的端点；但全文是个人体验随笔，没给具体配置步骤，能确立的交付有限。
原文
Using an open model feels surprisingly good
I've been using Claude and ChatGPT like the next guy for probably two years now. I've never been a huge "open software" nerd or anything like that. But just now, I got opencode working on my own inference endpoint and... it felt surprisingly good. It feels... freeing, somehow. I own the endpoint, and my data just goes from my laptop to there and back. It feels like it's mine. It's really nice.
The motivation for this was that I just got home and wanted to start on a little side project, but I don't have the best Claude or ChatGPT plan for my personal account. I work at Modal, and today we just launched Kimi K3 on managed endpoints, and I know Kimi K3 is supposed to be pretty solid, so instead of upgrading my Claude plan, I wanted to give it a try. (I didn't directly contribute to this feature, so I haven't gotten to play with it yet.)
Within about 5 minutes, I had opencode pointed at my own Modal endpoint and running. Spinning up opencode, I just felt a nice, empty blankness. The best way I can describe it is like opening vim after spinning a bunch of time in a big fancy editor. Or maybe like the tendrils tying me to other providers had been cut, and I could breathe freely. I'm being somewhat dramatic here but not exaggerating that much. It's weird, lol, and unexpected to me, which is why I wanted to write about it.
这条对你有帮助吗？