Exclusive-OpenAI sweetens private equity pitch amid enterprise turf war with Anthropic, sources say

By Milana Vinn and Krystal Hu
NEW YORK, March 23 (Reuters) - ChatGPT maker OpenAI is offering private-equity firms a sweeter deal than rival Anthropic as both artificial intelligence companies court buyout firms to form joint ventures aimed at raising fresh capital and accelerating adoption of enterprise AI products, according to people familiar with the talks.
OpenAI is offering private-equity firms a guaranteed minimum return of 17.5%, significantly higher than typical preferred instruments, two people familiar said. It is also offering early access to its newest AI models as it seeks to enlist investors like TPG and Advent for its joint venture, three sources said.
The company has recently doubled down on enterprise, an area where Anthropic has historically been stronger. By comparison, Anthropic’s enterprise-focused private-equity deal offered no such returns, the sources added.
OpenAI and Anthropic are competing for partnerships with buyout firms that would allow them to quickly roll out their AI tools to potentially hundreds of private, established companies owned by buyout firms. This would boost adoption of their models and encourage customer stickiness at scale.
The two companies are battling for more lucrative business customers to use AI as they race to position themselves for potential public listings as early as this year.
The joint venture structure could absorb high upfront costs associated with deploying engineers to customize models for clients, easing cost pressures on OpenAI and Anthropic ahead of going public, and providing clearer segment reporting that can support the IPO narrative, two of the people familiar with the discussions said.
OpenAI and Anthropic are racing to snap up similar types of partnerships with PE firms, a strategy that is new to the AI sector.
"There's a big race to lock in as much enterprise, as many desks as possible," said Matt Kropp at Boston Consulting Group’s AI unit, adding that once a company has a customized AI model integrated into its systems, it becomes much harder to switch to a competitor.
"I can see that there's a huge amount of scalability there.”
OpenAI, TPG and Advent declined to comment. Anthropic did not respond to a request for comment.
NOT FOR EVERYONE
At least two private-equity firms decided not to participate in either of the two joint ventures, citing concerns about the economics, flexibility and profit profile of the partnerships, two people said.
Thoma Bravo, one of the world’s largest software-focused buyout firms, decided not to participate after internal discussions led by managing partner Orlando Bravo, a person familiar with the decision said. Bravo raised questions about the long-term profit profile of joint ventures with OpenAI and Anthropic, adding that many of its portfolio companies are already deploying AI tools, the person said.