DeepSeek’s docs say V4 has a 1M context length. Is that actually usable in pract... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Grp1 22 days ago \| parent \| context \| favorite \| on: DeepSeek v4 DeepSeek’s docs say V4 has a 1M context length. Is that actually usable in practice, or just the model/API limit? Codex shows ~258k for me and Claude Code often shows ~200k, so I’m curious how DeepSeek is exposing such a large window.

lucrbvi 22 days ago [–]

They have added a lot of optimization focussing on the KV-cache, so they can have a much larger window without eating all the VRAM.

The 1M window might be usable, but it will probably underperform against a smaller window of course.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact