DeepSeek v4-flash: max thinking mode is both cheaper and faster than high

dosco · x · 2026-08-19

Developer dosco reports that with deepseek-v4-flash-latest, the "max" thinking mode is actually cheaper and faster than "high" mode for agentic workloads — a counterintuitive but practical data point for developers picking reasoning tiers.

Original post →

More from Models

Models channel →