Press Space to continue
Different models handle long-context requests with fundamentally
Press Space to continue
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.
open on x · 2 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.