BENCHMARKFirst benchmarks recorded: MiniMax M3 → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: Kimi K3 → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: DeepSeek V4 Pro → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: GLM-4.7 → Cortecs → ?4hBENCHMARKFirst benchmarks recorded: GLM-5.2 → Cortecs → ?4h

DeepSeek V4 Pro

1 providers · MoE · — context · 1 regions · all models →

DeepSeek V4 Pro across 1 providers

Same model. Different infrastructure. DEV DATA
TTFT spread1.0×Throughput spread1.0×Output price1.0×Tool reliability0.0 pts
TTFT381 ms381 msbest: Cortecs
Throughput285 tok/s285 tok/sbest: Cortecs
Output price$0.66/M$0.66/Mbest: Cortecs
Reliability90.3%90.3%best: Cortecs
Tool success100.0%100.0%best: Cortecs

DeepSeek V4 Pro — tool-calling benchmark

1 providers · 100.0% → 100.0% · 0.0 pt spread · DEV DATA
#ProviderToolsΔ bestRel.JSONTTFTP95Tok/s$ Out
01Cortecs100.0%—90.3%100.0%381 ms498 ms285$0.66
DeepSeek V4 Pro inference benchmark: fastest & cheapest providers · InferenceBench