DeepInfra Raises $107M Series B to Scale AI Inference Cloud Processing 5T Tokens/Week

DeepInfra, a purpose-built cloud platform for high-throughput AI inference, raised $107 million in Series B funding co-led by 500 Global and Georges Harik (early Google engineer). The platform processes nearly 5 trillion tokens per week with 25x growth since its Series A, and revenue has tripled since the beginning of 2026. DeepInfra supports 190+ open-source models and is SOC 2 and ISO 27001 certified with zero data retention. Founded in 2022 by the team behind imo messenger (200M+ users), DeepInfra is headquartered in Palo Alto with CEO Nikola Borisov. Investors include NVIDIA, Samsung Next, Supermicro, and Upper90.