Epoch 测 Astra 长上下文延迟与定价拐点

Epoch AI @EpochAIResearch原推发布于 2026.09.11

在 X 上打开原推

Earlier this week, we showed that GPT-5.6 and Claude 5 exhibit very different long-context TTFT scaling, which corresponds to their different pricing structures at long context lengths. OpenAI recently released GPT-6 Astra, which shows the same pattern of increased API pricing beyond 272k input tokens. We collected additional latency measurements, which show a similar curvature to that of GPT-5.6 models.

这条是引用着另一条写的：x.com/1529761561170124800/status/209743297517256…