DeepSeek v4.1 flash preview spotted running at ~300 tok/s, vision still missing
kevinkern · x · 2026-09-10
A preview endpoint for DeepSeek v4.1 flash has been spotted running at roughly 300 tokens/s. The preview endpoint still lacks vision support, but the poster hopes the official release will ship with multimodal capabilities. Details remain unconfirmed pending an official launch.
More from Models
- InclusionAI's free Ling 3.0 Flash Sante: a 124B MoE medical model with 262K context on OpenRouter — FellMentKE · 2026-09-10
- DeepSeek V4.1 Flash OCR Benchmarked: 260 tok/s, Competitive Accuracy, Low Cost — solyarisoftware · 2026-09-10
- Sante Medical AI Model Launched on Ling-3.0-flash: Focus on Reasoning, Safety, Evidence — FellMentKE · 2026-09-10
- Sante Medical AI Model Launched on Ling-3.0-flash: Focus on Reasoning, Safety, Evidence — FellMentKE · 2026-09-10
- Sante Medical AI Model Launched on Ling-3.0-flash: Focus on Reasoning, Safety, Evidence — FellMentKE · 2026-09-10
- Yoav Goldberg: 880K GPU-Hours vs a Few Hundred Prompted LLM Hours for Same Math Result — yoavgo · 2026-09-10