Baseten claims fastest inference for DeepSeek V4 Pro

baseten · x · 2026-08-19

Baseten claims to be the fastest inference provider for DeepSeek V4 Pro 0813 on Artificial Analysis, achieving 147 TPS. The company's engineers continue to optimize the model to deliver the highest throughput and lowest latency.

Original post →

More from Infra

Infra channel →