DeepSeek 4.1 Flash and Mercury 3: Speed-First Models
Oct 19, 2026 · 530 messages · 72 active members
New providers are serving DeepSeek 4.1 Flash at 280-400+ tps for coding workloads at ~$0.60/M tokens, well above OpenRouter's advertised numbers, with fewer refusals than OpenAI. Inception's Mercury 3 is clocking ~1000 t…
Read full digest →