openrouter, "together" provider is fastest (165 t/s at the time of writing) and has ZDR and all

https://openrouter.ai/deepseek/deepseek-v4.1-flash?endpoint=...

Sadly, there is no way to tell if this is running with real weights or being heavily quantized.

Eh, it's also one of the providers with "blind" vision models https://mmoustafa.com/blog/so-you-want-to-use-openrouter/