Tensormesh Raises $20M Seed to Cut AI Inference Costs

Fundraise Insider tracks newly funded startups each week and delivers verified C-suite contacts straight to your inbox, so you reach the right people while the funding is still fresh. See pricing.

Tensormesh has announced $20 million in new funding from investors including AMD Ventures, CoreWeave, NVentures (the venture arm of NVIDIA), Valley Capital Partners, and Laude Ventures. The financing extends the company’s Seed round and brings total funding to $24.5 million.

The company was founded by faculty, PhD researchers, and alumni from the University of Chicago, UC Berkeley, and Carnegie Mellon. It is led by Junchen Jiang, a University of Chicago faculty member and co-creator of LMCache.

Alongside the funding, Tensormesh announced general availability of Tensormesh Inference, its flagship SaaS inference platform. The product addresses one of the most expensive problems in enterprise AI: recomputing work that GPUs have already processed. Tensormesh stores and reuses computed results through KV caching, which removes redundant computation and delivers reductions in latency and GPU spend of up to ten times.

The platform includes a Cost Savings Dashboard that shows the financial impact of caching in real time, tracking exactly how much has been saved. It monitors cache hit rate, the ratio of cached to total prompt tokens, and converts that figure into a continuously updated dollar amount.

When a request is served from the KV cache, the cached input tokens cost nothing. Across all of Tensormesh’s serverless deployments, cached input tokens are billed at zero. The company frames this not as a promotional rate but as a permanent part of how it prices the platform.