DeepSeek-V4-Flash Update

	DeepSeek-V4-Flash Update(api-docs.deepseek.com)
	343 points by dnhkng 5 hours ago \| 170 comments
	tl;dr: DeepSeek-V4-Flash is now in public beta, accessed via the `deepseek-v4-flash` model name. It focuses heavily on agent capabilities, posting scores like 82.7 on Terminal Bench 2.1, 66.0-equivalent SWE work, and 54.4 on DeepSWE, and natively supports the Responses API with Codex adaptation. Architecture and size are unchanged from the Preview—only post-training was redone—and a full V4-Pro release is expected soon.
	HN Discussion: ↑Flash model is excellent for daily coding/agent tasks due to speed and low cost ↑Benchmarks are impressive given the smaller parameter count outperforming larger models ~DeepSeek works well for familiar tasks but other models preferred for unfamiliar domains ~Concerns about data privacy leaking codebase information to China via DeepSeek API •Questions about optimal model selection strategy across different providers