Alphabet is reportedly working on a next-generation AI server chip designed to make its Gemini models faster and significantly more power-efficient.
According to a report from The Information, the custom chip is internally known as “Frozen v2” and is expected to launch sometime in 2028.
The report claims Frozen v2 could deliver between six and ten times greater efficiency than Google’s current AI chips, based on the number of AI tokens generated for each unit of power consumed. If those figures prove accurate, the new hardware could dramatically reduce the energy required to run Google’s growing portfolio of AI services.
Google did not confirm the existence of the chip but also did not deny the report. In a statement, the company said its engineering teams are continuously researching and testing new technologies to improve performance and efficiency. Google added that while not every project reaches production, its strategy of designing both hardware and software together helps create highly optimized AI systems for real-world workloads.
The development reflects a broader trend across the AI industry, where major companies are investing heavily in custom silicon instead of relying entirely on third-party hardware. Building specialized AI chips allows companies to improve performance, lower operating costs, and reduce dependence on Nvidia, whose processors have long dominated the AI market and remain in extremely high demand.
Several leading AI firms are following the same path. OpenAI recently introduced its first custom inference chip, called Jalapeño, while reports indicate Anthropic is exploring a chipmaking partnership with Samsung to strengthen its own AI infrastructure.
The move also comes as Alphabet continues making enormous investments in artificial intelligence. Earlier this year, Google said it expects to spend between $180 billion and $190 billion to expand its AI capabilities. Developing more efficient custom chips could help the company lower long-term operating costs and demonstrate that its massive AI investments will deliver meaningful returns.





