Hugging Face 為 PRO 訂閱者推出專屬推理服務：更高速率、支援大型開源模型
Original: Inference for PROs
The Hugging Face official blog has announced a new "Inference for PROs" upgraded service for PRO subscribers (at $9 per month). This…
Hugging Face 宣布為每月 9 美元的 PRO 訂閱用戶升級 Serverless 推理 API 服務。PRO 用戶將享有更高的速率限制、更低的延遲，並能直接調用 Llama 2、Falcon 與 StarCoder 等熱門大型開源模型。這項升級讓開發者在部署專屬端點前，能以極低成本進行高效的原型開發與測試。
The Hugging Face official blog has announced a new "Inference for PROs" upgraded service for PRO subscribers (at $9 per month). This service is designed to address the rate limit and model size restrictions that developers frequently encounter when using the free Serverless Inference API for prototyping.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.