精选理由
Fireworks 直接跑 GLM 5.2 权重，1M 上下文还不存你的数据，做编码代理很稳。
Fireworks AI 宣布支持 GLM 5.2 模型，直接运行模型权重而非通过路由转发到其他平台。他们承诺零数据保留、生产级延迟，并开放 1M 上下文窗口。该服务面向长时编码代理，强调稳定性而非基准排名。
原文 · Fireworks AI
You may have seen other platforms announce day-zero support within minutes of weights dropping, but ...
You may have seen other platforms announce day-zero support within minutes of weights dropping, but there is a key difference between inference providers and routers. Routers forward your GLM 5.2 calls to someone else’s endpoint (typically the model lab’s own API). Fireworks runs the weights directly: end‑to‑end serving path, zero data retention, production‑grade latency. For long‑horizon coding agents, a clean 1M window + stable infra beats leaderboard screenshots. 💬 1 🔄 0 ❤️ 9 👀 681 📊 3 ⚡