Model APIs now process nearly 32 billion tokens per minute
我们的第一方模型 API 现在每分钟处理近 320 亿个 token——比上一季度多 40%,是一年前的 4 倍多。
English original
Our first-party model APIs are now processing nearly 32 billion tokens per minute — 40% more than last quarter and more than four times what we processed a year ago.
在2026年第三季度财报电话会上