# Nvidia-backed Nebius buys Inferize to cut AI inference GPU costs

Digest AI · Hardware & Compute · published 2026-10-01T05:30:00Z

Canonical: https://digestai.news/story/nvidia-backed-nebius-buys-inferize-to-cut-ai-inference-gpu-costs

## Summary

Inferize’s technology targets cold-start delays, which leave GPUs unused while models load or capacity scales. The deal integrates Inferize’s tools into Nebius Token Factory, a managed production-inference platform, aiming to improve GPU utilization and lower infrastructure costs per AI token.

Inferize CEO Guy Bortnikov said the startup’s prototype was built in three months after its January 2026 founding. Nebius previously added model and system optimizations through acquisitions like Eigen AI and Clarifai. The deal terms remain undisclosed.

## Key points

- Inferize’s tech reduces GPU idle time during AI inference cold starts, improving utilization
- Acquisition integrates into Nebius Token Factory, its managed production-inference platform

## Why it matters

Lowering idle GPU costs could make cloud AI inference more cost-effective for data centers and startups.

## Sources

1. [Nvidia-Backed Nebius Acquires Inferize To Reduce Idle GPU Costs Across AI Inference Workloads](https://finance.yahoo.com/technology/ai/articles/nvidia-backed-nebius-acquires-inferize-124902034.html) (finance.yahoo.com, 2026-10-01)

## Cite

Digest AI, "Nvidia-backed Nebius buys Inferize to cut AI inference GPU costs", 1 October 2026, https://digestai.news/story/nvidia-backed-nebius-buys-inferize-to-cut-ai-inference-gpu-costs

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/nvidia-backed-nebius-buys-inferize-to-cut-ai-inference-gpu-costs.json