DeepSeek-V4-Flash-0731

DeepSeek-V4-Flash-0731 is a 284B-parameter Mixture-of-Experts language model with 13B activated per token and a 1M-token context window, optimized for agentic workflows, coding, tool use, and long-context reasoning. It is the official updated release of the V4-Flash series, superseding the earlier preview and offering substantially enhanced agentic capabilities. Source: supabase.