Fuck, the wait is finally here for DeepSeek’s native multi-modal model.
I tested it in PI Agent, keeping the base_url unchanged, and setting the model name to deepseek-v4.1-flash-expires-on-0910 to call it DeepSeek V4.1 Flash is currently in internal testing. It adopts a new model structure, native multi-modal support, stronger capabilities, faster speed, and lower cost.
Daigo riding a bicycle animation generated by DeepSeek V4.1 Flash
Prompt: Write an html, the content is a 2D animation of Daigo riding a bicycle, the effect is as follows 👇What do you think?
Free access to 8+ top AI models
Essentially, you can test models from Google, OpenAI, Anthropic, DeepSeek, Qwen and others all in one place how to started: 1. go to 2. sign up with Gmail 3. used my ref code: 96CCZGV5 3. create your API key 4. choose a
DeepSeek is getting stupider and stupider. Do you still dare to use such a model?
You have reached the end of the archive
All of deepseek