News for hackers. Stuff that matters.

A comment on DeepSeek v4.

Re:DeepSeek v4 by Grp1 on Friday April 24, 2026 @05:09AM (#47887632)
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.

[ Parent | on HN ]
Re:DeepSeek v4 by lucrbvi on Friday April 24, 2026 @05:12AM (#47887656)
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.

[ Parent | on HN ]