DeepSeek V4 Pro tokens per second

Live benchmark data for DeepSeek V4 Pro on opencode-go. Speed, latency, and reliability — benchmarked every ~10 minutes.

Latest TPS: —
24h avg TPS: —
TTFT: —
24h reliability: 0%
Intelligence Index: 44.3
Last tested: —

Tokens per second over time

Time to first token over time

Speed is measured as output tokens ÷ generation time. Each benchmark fires one streaming chat completion with a fixed ~300-token prompt, every ~10 minutes. Full methodology →