跳到正文
🚨 AI News | TestingCatalog· @testingcatalog · X·· 5 天前AI 评分58
AI 导读

Hugging Face 将语言模型推理请求切换至 OpenRouter,由后者按实时价格、速度和可靠性为每次调用选择供应商,首个供应商失败时自动重试其他供应商。据 OpenRouter 说明,请求统一使用同一个 Hugging Face token 和 API,并可通过 Broadcast 把请求轨迹存入 Hugging Face Storage,与模型一起放在 Hub 上供评测或微调使用。

正文 · 原文

OpenRouter ❤️ HuggingFace

HuggingFace switching its inference provider to OpenRouter!

“Requests made to language models now go through OpenRouter, which picks the best provider for each call based on live price, speed and reliability, and retries on another provider if the first one fails.”

HuggingRouter 👀

引用OpenRouter@OpenRouter
Open models on @huggingface now run through OpenRouter. Each request goes to the provider with the best price, speed, and uptime for that model, with automatic failover. Everything runs on the same Hugging Face token and API. You can also send your traces to Hugging Face Storage with Broadcast, so your requests live on the Hub next to your models, ready for things like evals or fine-tuning.
在 X 查看被引用的帖子

来源:🚨 AI News | TestingCatalog · x.com