What's that in summary?

Not the person you're replying to, but judging by the emphasis on the cost of cached input tokens in the OP article, I'd guess it has to do with DeepSeek v4.1's KV cache efficiency. It uses <1000 bytes per token, so they're able to get 1M token context in under a GB.

Edit: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/...

	▲	ChromeUltron a day ago \| parent [-]
		just goes to show that OpenAI in fact did not innovate on a single thing for the better part of a year (one could argue two) and instead keeps immitating what it sees doing others successfully with the tech, all in a very transparent attempt to get people lubed up for their IPO.