Inferact, Inc.

Inferact, based in the US, specializes in providing advanced AI solutions through its open-source large language model inference engine, vLLM, enhancing the efficiency of AI deployments for various industries. Founded in 2025 by co-founders Simon Mo, Woosuk Kwon, Kaichao You, Roger Wang, and Joseph Gonzalez, Inferact is located in San Francisco, US, and focuses on creating AI infrastructure to optimize inference processes. In January 2026, Inferact raised USD 150 million in seed funding co-led by investors Andreessen Horowitz and Lightspeed Venture Partners, with participation from other investors Sequoia Capital, Altimeter Capital, Redpoint Ventures, and ZhenFund. The seed funding values Inferact at USD 800 million post-money.

Inferact's primary offering is vLLM, an open-source large language model (LLM) inference engine designed to enhance the capabilities and efficiency of AI deployments. Launched through extensive community collaboration, vLLM serves as a bridge between advanced AI models and varied hardware infrastructures, accommodating over 500 model architectures and running seamlessly on more than 200 types of accelerators. The end-use cases targeted by Inferact include applications in real-time inference, reinforcement learning training loops, and synthetic data generation, addressing the growing demand for efficient AI model serving. This product primarily caters to a diverse client base that spans frontier research labs, hyperscalers, and startups, facilitating scalable AI solutions for millions of users globally.

Inferact aims to expand its geographic reach, serving markets across North America, Europe, and Asia. Inferact’s revenue model centers around partnerships and enterprise subscriptions to its core product, vLLM. Clients engage in transactions that typically involve accessing the vLLM infrastructure to optimize their AI inference processes, with revenue generated through annual contracts or usage fees based on model complexity and scale. The company collaborates closely with both model and hardware vendors to ensure immediate compatibility upon new architecture releases, allowing for a streamlined onboarding process for clients.

While specific pricing details are proprietary, the revenue structure reflects the firm’s commitment to providing scalable solutions to enterprises looking to integrate advanced AI capabilities within their operations. This model enables Inferact to maintain a strong presence in the fast-evolving AI landscape, positioning them as a critical player in the open-source inference market. In January 2026, Inferact raised USD 150. 00 mn in Seed funding to expand its AI infrastructure, add engineering staff, and support ongoing product development.

The company is also targeting expansion into North American, European, and Asian markets by 2027, strengthening its global footprint. The funding will facilitate these initiatives, enabling Inferact to enhance its product offerings and reach a broader client base.