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.
More from Models
- Forcing models to always max effort is like humans evolving on Adderall, researcher argues — voooooogel · 2026-09-11
- Pushing models to always show 'maximum effort' drags along its corollaries, dev argues — voooooogel · 2026-09-11
- Claude is the distillation target of choice because agentic RL seed data is scarce — teortaxesTex · 2026-09-11
- Why Chinese labs distill from Anthropic: Claude's agent data is the scarce training signal — teortaxesTex · 2026-09-11
- ApprenticeBench: closed model scores 72% vs open Kimi K3 at 18% on real jobs — ysu_nlp · 2026-09-11
- CursorBench 4.0 launches; Muse Spark 1.3 matches Sol at under 40% the cost — jyangballin · 2026-09-11