DeepSeek V4.1 Flash over the API is *really* fast!
🤯 Some details: • new architecture + native multimodality • 1M context window • same price as v4 Flash For me it seems to be (over)thinking a lot though.
The beta version of DeepSeek 4.1 Flash has recorded very fast performance in tests.
See the output speed test in this video: 👇
Deepseek-v4.1-flash I'm really curious to understand the architecture behind the scenes.
🤔 Model is really fast as you can see in the video! I've got an average decoding speed of around 350 t/s. BTW it is clearly experimental and: - currently, the model is under heavy load and
Quite beautiful: DeepSeek V4.1 Flash hands-on 3D test, this Fuji Sakura station is already playable!
The low-model station building, pink cherry blossoms, railway tracks, and fences were all set up at once, and day and night switching, sunny and rainy, and animation pauses were all connected.
You have reached the end of the archive
All of deepseek