跳到正文

Hugging Face 通过 OpenRouter 路由 Inference Providers 请求

Hugging Face Blog当事人·· 1 天前精选Hugging Face and OpenRouter join forces to make open-weight models easy to run
打开原文
原文
图片来自 Hugging Face Blog
谁
Hugging Face
引文
Today, we are switching Inference Providers from our own custom router to OpenRouter's.

发生了什么

Hugging Face 已将 Inference Providers 的语言模型请求切换至 OpenRouter。OpenRouter 会根据实时价格、速度和可靠性指标选择提供商,并在请求失败时使用其他提供商重试。用户可以继续使用原有的代码和 Hugging Face 令牌,但无法再为语言模型使用自己的提供商 API 密钥。图像、视频和音频生成仍直接通过 Hugging Face Inference Providers 运行。

推荐理由

当某个提供商失败时,语言模型请求现在可以通过其他提供商重试,同时用户仍可设置路由偏好或禁用特定提供商。用户无法再为这些模型使用自己的提供商 API 密钥。

接下来读什么

查看这件事的完整进展Hugging Face Routes Language Model Requests Through OpenRouter

这件事到目前为止

Hugging Face has switched its Inference Providers' language model requests from its own custom router to OpenRouter, which selects a provider for each call based on live price, speed, and reliability measurements and retries with another provider if a request fails. Users can keep their existing code and Hugging Face token, though language model requests are now billed to their Hugging Face account or organization and can no longer use a user's own provider API keys. PRO users receive $2 in monthly credits, while Team and Enterprise organizations receive $2 per seat. Image, video, and audio generation continue to run directly through Hugging Face Inference Providers without going through OpenRouter.

这条收录于 11月17日 AI 日报看这一期日报的全部内容