Claude adds Fast mode: Opus quality at 2.5x the speed
By Steven Van ·
The new setting costs more per token but suits latency-sensitive work like live debugging.
Fast mode is a new response speed for Claude: the same quality as Opus, at roughly 2.5x the speed, billed at a higher per-token rate. Anthropic describes it as suited to work where latency matters more than cost, such as rapid iteration, live debugging, or other time-sensitive tasks.
Claude
AI assistant by Anthropic — write, analyze, code, and create with one of the most capable large language models available.
View Claude →