DeepSeek V4.1 Flash goes live on Baseten with 1M context and vision support

baseten · x · 2026-09-11

Baseten announced day-0 availability of DeepSeek V4.1 Flash on its Model APIs, claiming it is smarter, faster, and more efficient than DeepSeek v4 Pro 0813. The model supports text and vision input, offers a 1M-token context window, is US-only with ZDR (zero data retention), and Baseten Loops support is coming soon.

Original post →

More from Models

Models channel →