DeepSeek V4.1 Flash Tested: Blazing 350 Tokens/s but Still Experimental
Hands-on tests of DeepSeek's experimental V4.1-Flash model show decoding speeds of roughly 300-400 tokens per second at competitive prices, though reviewers note it remains early-stage and prone to overthinking.
2026-09-08 ~ 2026-09-09 · 2 related posts
- Episode 1: DeepSeek V4.1 Flash Opens Limited Beta with New Architecture and Native Multimodality(2026-09-08, 12 posts)
- Episode 2: DeepSeek Opens V4.1 Flash Beta with Aggressive Pricing(2026-09-08, 4 posts)
- Episode 3: DeepSeek V4.1 Flash Tested: Blazing 350 Tokens/s but Still Experimental(2026-09-08, 2 posts)
- Episode 4: DeepSeek cuts V4-Flash API pricing, off-peak cache hits drop to 0.02 yuan(2026-09-08, 6 posts)
- Episode 5: DeepSeek V4.1 Flash beta shows big gains in vision and cybersecurity(2026-09-09, 3 posts)
- DeepSeek V4.1-Flash hands-on: 350 t/s decoding speed but still very experimental — teortaxesTex · 2026-09-08
- DeepSeek V4.1 Flash tested: 300-400+ tok/s, cheap and fast, but prone to overthinking — WorldofAI · 2026-09-09