Amazon's AI Chips Are Driving Growth. Here's Why That Could Accelerate

Key Points

Demand for Amazon's AI chips remains high.

Even so, the company won't topple Nvidia as the market leader.

There are other reasons to invest in Amazon.

• These 10 stocks could mint the next wave of millionaires ›

Amazon (NASDAQ: AMZN) boasts a diversified business. The company has made it a habit of establishing itself as a leader in most of the markets where it operates. The list includes e-commerce, cloud computing, streaming, and digital advertising. Could the tech leader do the same in the market for artificial intelligence (AI) chips? Recent comments from the company's CEO, Andy Jassy, suggest that Amazon's AI chips are becoming a growth powerhouse, and there could be even more upside ahead. Here's what investors need to know.

Will AI create the world's first trillionaire? Our team just released a report on the one little-known company, called an "Indispensable Monopoly" providing the critical technology Nvidia and Intel both need. Continue »

A booming business

Amazon doesn't sell its chips to external customers. The company installs them in its data centers and allows its cloud customers to train or deploy AI models using its custom chips, which include Trainium and Graviton. Why wouldn't Amazon just use AI chips designed by the market leader, Nvidia (NASDAQ: NVDA)? The reality is that Amazon is likely one of Nvidia's biggest customers, but the e-commerce specialist can achieve several goals by also designing and offering its own hardware. First, as the market leader with the best-performing chips, Nvidia possesses tremendous pricing power.

Having to pay a premium price undercuts Amazon's margins. However, the company's internally developed chips could help address this issue. As Jassy said, Trainium2, for instance, offers 30% better price performance than comparable GPUs (Graphics Processing Units). Second, the incredible demand for Nvidia's AI chips means that the company is sometimes supply constrained, which could be a problem for Amazon. Once again, this is an issue that it can address by designing its own chips in-house.

Amazon is already seeing tremendous success with this strategy, and things are only getting better. The company pointed out that Trainium2 is pretty much fully booked, as is Trainium3, which hasn't been available that long. Trainium4, which isn't even available yet (and won't be for another 18 months), is already being reserved. Meanwhile, Amazon also expects margin expansion thanks to its Trainium chips. As Jassy said:

Trainium will save us tens of billions of dollars of capex each year and provide several hundred basis points of operating margin advantage versus relying on other chips for inference.

That's very good news for investors.

More growth ahead?

Amazon's efforts should continue paying off. The company said that within two years, there is a good chance it could start selling its chips to external customers rather than limiting them to its cloud customers. Earlier this year, Jassy estimated that if Amazon did that, its AI chip business would already boast a $50 billion annual run rate. It could be much higher in a couple of years, and if Jassy is right, it could become a meaningful contributor to Amazon's financial performance. There is another reason Amazon's design of its own AI chips could help boost its cloud business: it arguably strengthens the company's switching costs.

Amazon designed Trainium as an integrated stack combining custom AI chips, AWS (Amazon Web Services) software tools, and cloud infrastructure. As customers optimize AI workloads around Trainium and the AWS ecosystem, migrating to another cloud provider could become increasingly costly. Now, Amazon is unlikely to dethrone Nvidia as the market leader, even if it starts selling its chips to external customers. Nvidia's chips are still the top-performing ones.

Further, Amazon's projected margin expansion depends on whether demand remains high. Designing AI chips is capital-intensive, and if demand slows, the company's margins might decline. Even with these potential issues, Amazon remains an attractive stock, especially once we consider the totality of the business. Beyond its cloud computing segment -- whose sales growth climbed to a multi-year high in the first quarter -- Amazon's digital advertising business is also performing well, as are its core e-commerce operations.

The tech leader has attractive growth opportunities in these industries, and given its leading position and competitive edge, it is well-positioned to capitalize on them over the long run. In short, Amazon is a great pick for long-term investors.

Don’t miss this second chance at a potentially lucrative opportunity

Ever feel like you missed the boat in buying the most successful stocks? Then you’ll want to hear this.

On rare occasions, our expert team of analysts issues a “Double Down” stock recommendation for companies that they think are about to pop. If you’re worried you’ve already missed your chance to invest, now is the best time to buy before it’s too late. And the numbers speak for themselves:

Nvidia:if you invested $1,000 when we doubled down in 2009,you’d have $569,198!Apple:*if you invested $1,000 when we doubled down in 2008,you’d have $55,783!Netflix:if you invested $1,000 when we doubled down in 2004,you’d have $460,826!

Right now, we’re issuing “Double Down” alerts for three incredible companies, available when you join Stock Advisor, and there may not be another chance like this anytime soon.

**Stock Advisor returns as of May 12, 2026. *

Prosper Junior Bakiny has positions in Amazon and Nvidia. The Motley Fool has positions in and recommends Amazon and Nvidia. The Motley Fool has a disclosure policy.

The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.