Roubaix – November 20, 2025 – OVHcloud, a global cloud player and the European Cloud leader, today announced it has selected SambaNova, a next generation AI infrastructure leader, as the building block to complement its inference portfolio of solutions with a focus on ultra-low latency inference.
OVHcloud believes that organisations building next-generation AI workloads face increasingly sharp constraints: sequential LLM calls that introduce latency bottlenecks, user-facing applications that require immediate responses, and operational pipelines that must scale to millions of inferences with strict performance guarantees for time to first token and time per output token.
The OVHcloud and SambaNova partnership unlocks a wide range of use cases where every millisecond matters. In sectors such as financial trading, cybersecurity, industrial automation, logistic optimisation, monitoring and much more, slow inference can mean missed opportunities, operational blind spots, or degraded user experience.
OVHcloud AI Endpoints powered by SambaNova’s SambaStack platform enables the Group to add production-grade capabilities to its endpoints characterised by exceptional performance, fast inference, energy efficiency and availability with a 99.8% uptime SLA.
SambaNova's fast inference platform will power OVHcloud's AI Endpoints, designed for most demanding workloads requiring the fastest, most reliable, and largest-scale inference. Through this new solution, OVHcloud aims to address new endpoints flavors: real-time endpoints with guaranteed performance and batch API to sustain tremendous number of calls when real-time is not needed. Resulting for the end users in answers delivered with fastest possible time to first byte and time per output token.
Complementing the current backbone of GPU powered AI Endpoints sessions, SambaNova new inference node will offer customers a blazing fast experience thanks to reconfigurable dataflow units (RDUs) that are purpose-built chips for AI. Not only does SambaNova technology delivers high tokens per kilowatt-hour, it also proves ideal in terms of efficiency favouring resource utilization and datacentre density.
With blistering fast inference speeds, SambaNova powered AI Endpoints relies on the largest open-source models perfectly architected for running demanding agentic workloads and low latency for real time use cases such as AI agents, live translation, agent to agent use but also batch API for asynchronous use-cases including crawling, vector-db generation, dataset refreshing and massive batch operations.
”Choosing SambaNova was a deliberate decision to provide our customers with an unrivalled inference experience,” said Octave Klaba, founder and CEO of OVHcloud. ”Their technology delivers the raw power and efficiency needed for the most intensive AI workloads. This partnership allows us to run more models, in a smaller footprint leading to AI inference with better utilisation.”
”SambaNova’s collaboration with OVHcloud underscores how we’re setting a new standard for AI performance and efficiency at scale,” said Rodrigo Liang, Co-founder and CEO of SambaNova. ”Together, we’re giving enterprises the power to deploy large-scale AI models faster and more reliably than ever before. This partnership opens the door to breakthrough innovation, helping customers turn cutting-edge AI into real-world results.”
The SambaNova powered AI Endpoints service is a cornerstone of OVHcloud's strategy to provide a comprehensive, high-performance AI inferencing platform, catering to developers or enterprise customers seeking the best possible performance, support, and advanced features for their critical AI applications.
SambaNova powered inferencing will be available by end of year from regions located in France with future deployments planned in Europe. Service billing will be a pay-as-you-go model with a required commitment.
OVHcloud is a global cloud player and the leading European cloud provider operating over 500,000 servers within 46 data centers across 4 continents to reach 1,6 million customers in over 140 countries. Spearheading a trusted cloud and pioneering a sustainable cloud with the best performance-price ratio, the Group has been leveraging for over 20 years an integrated model that guarantees total control of its value chain: from the design of its servers to the construction and management of its data centers, including the orchestration of its fiber-optic network. This unique approach enables OVHcloud to independently cover all the uses of its customers so they can seize the benefits of an environmentally conscious model with a frugal use of resources and a carbon footprint reaching the best ratios in the industry. OVHcloud now offers customers the latest-generation solutions combining performance, predictable pricing, and complete data sovereignty to support their unfettered growth.
SambaNova enables enterprises to rapidly deploy state-of-the-art generative AI capabilities. Headquartered in Palo Alto, California, SambaNova was founded in 2017 by industry veterans from Sun/Oracle and Stanford University. The company is backed by top-tier investors including SoftBank Vision Fund 2, BlackRock, Intel Capital, GV, Walden International, Temasek, GIC, Redline Capital, Atlantic Bridge Ventures, and Celesta.
For more information, visit sambanova.ai or contact info@sambanova.ai.
Julien Jay
Communications & Public Relations Manager
media@ovhcloud.com
+33 (0)7 61 24 46 67
Virginia Jamieson
Head of Communications, SambaNova
virginia.jamieson@sambanova.ai
650-279-8619