Jensen Huang-led Nvidia is in talks to invest in Perplexity AI as part of an equity funding round that would value the American startup at more than USD 30 billion.
As per the report from The Information, the successful completion of the funding round would increase Perplexity’s valuation by more than 50% from its previous financing a year ago.
Perplexity’s annualized revenue has risen to more than USD 750 million from less than USD 250 million at the start of 2026. “Perplexity Computer,” a cloud-based AI agent, has driven part of the revenue growth by automating computer-based tasks for professionals.
Earlier this year, the startup, led by Aravind Srinivas, signed a USD 750 million agreement with tech giant Microsoft to use the latter’s Azure cloud service.
As per Srinivas’ interview with CNBC in June, Perplexity is planning to go public in 2028 regardless of how the market receives the listings of Anthropic and OpenAI.
The startup’s high-profile backers, along with Nvidia, include Amazon founder Jeff Bezos and Japan’s SoftBank Group.
The startup, in July, made public its plans of using Nvidia’s new central processing units, as the chip giant works to broaden its market and take on entrenched players such as Intel and Advanced Micro Devices (AMD).
Nvidia expects to generate USD 20 billion in sales from its “Vera CPU,” that the company defines as a more generic computing chip than the AI-specific offerings, by the end of this fiscal year.
The Vera chips are part of Nvidia’s efforts to diversify sales as AI companies like OpenAI and DeepSeek make their own AI chips.
Nvidia is entering a crowded market for CPUs long dominated by Intel and AMD, which supply CPUs for everything from laptops to web servers. However, as per the Huang-led venture, many of those chips were designed before the rise of what are known as “AI Agents” that can carry out complex tasks on their own after receiving instructions from their human users.
As per Nate Kupp, Perplexity’s Vice President for Computer Enterprise and Infrastructure, unlike human users of CPUs, who take breaks between tasks, AI agents work non-stop. To prove his point, he cited one incident in which Nvidia’s CPU carried out AI agent coding tasks about 1.5 times faster than traditional CPUs.
Kupp stated, “Vera truly impressed us as an ideal match for many of our core workloads.”