[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![AlpacaNetworkAI Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1808408844747366400.png) Alpaca Network [@AlpacaNetworkAI](/creator/twitter/AlpacaNetworkAI) on x 20.5K followers
Created: 2025-07-10 21:23:02 UTC

DeepSeek-R1 (DeepSeek-AI)

What it is – A XXX B-parameter Mixture-of-Experts model with only XX B “active” parameters at inference time and a huge XXX k token context window. Trained purely with reinforcement learning, it set a new open-source bar for chain-of-thought reasoning in maths, code and GPQA, often matching or beating OpenAI o1 in public leaderboards.



![](https://pbs.twimg.com/media/Gvhq2SHakAAsOmm.jpg)

XXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1943420723718164766/c:line.svg)

**Related Topics**
[o1](/topic/o1)
[open ai](/topic/open-ai)
[context window](/topic/context-window)
[token](/topic/token)
[inference](/topic/inference)
[deepseekr1](/topic/deepseekr1)
[alpaca](/topic/alpaca)

[Post Link](https://x.com/AlpacaNetworkAI/status/1943420723718164766)