Event ·Official first-hand

亚马逊云服务在 bedrock 上对比 openai 模型成本与效果

这篇文章分享了一个开源基准测试工具，用于衡量在亚马逊 bedrock 平台上使用 openai 模型时，每百万令牌的成本、正确答案的成本以及基于评分标准的交付质量。

Current read

亚马逊云服务分享了一个工具，帮你对比 openai 模型在 bedrock 上的成本和效果，不是只看单价，而是看实际产出。

10 sources58° AI heatLast updated 2026/9/11 18:24:38

Evidence

10 sources

Primary sourceAWS Machine Learning Blog

2026/9/11 18:24:38View source

Related source 1宝玉

2026/9/11 00:15:28View source

Related source 2shao__meng

2026/9/10 00:28:55View source

Related source 3Julien Chaumond

2026/9/10 16:07:30View source

Related source 4@OpenAIDevs

2026/9/10 17:20:58View source

Related source 5HeyGen

2026/9/10 17:55:10View source

Related source 6向阳乔木

2026/9/11 17:57:33View source

Related source 7Clement Delangue

2026/9/11 20:51:54View source

Related source 8Decoder

2026/9/12 10:08:43View source

Related source 9elvis

2026/9/12 15:40:47View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story