Surprise landing of DeepSeek v4.1-flash.
I am blown away by the quality improvement compared to v4-flash. Huge jump. It is FAST peaked speed 427 t/s. It used 112k tokens and 20 turns taking 7:41. Cost 0.037 Unbelievable result for 4 cents. deepseek_ai is cooking.
New video online - DeepSeek V4.1 Flash actual measurement: nearly 200 million Tokens spent about 35 yuan, what is the effect?
3D modeling and writing are good. I really like the details of the Riverside Scene during the Qingming Festival, the texture of the Hello Kitty furniture, and the interaction of the IKEA installation webpage. The problem is that the waiting time is long, multiple tasks take more than an hour to run, and the price is not cheap during peak periods. Video organized 8…
Cline is hands-down one of the best AI coding agents you can run inside VS Code right now — and the best part?
You don't need to pay a single cent to use it. In this video, I'll show you exactly how to set up Cline for 100% free!
Deepseek v4.1 flash vs secret model
Tested both with the same prompt at the highest reasoning available v4.1 flash took 2 hours to finish both tests and cost $2.60 secret model finished both in 30 minutes, can’t reveal cost yet v4.1 flash spent a lot of time overthinking
You have reached the end of the archive
All of deepseek