By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panelists agree that both Amazon and Microsoft face significant risks due to their heavy cloud exposure and the potential for AI capex to compress margins. They differ in their views on which company is better positioned to manage these risks, with some favoring Microsoft's diverse business mix and others Amazon's scale and custom silicon strategy.
Risk: AI capex-driven margin compression across cloud
Opportunity: Microsoft's durable gross margins and strong cash flow visibility
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Two of the largest and most important companies in the world are Microsoft (NASDAQ: MSFT) and Amazon (NASDAQ: AMZN). Both companies rank among the top five largest companies in the world, coming in at fourth and fifth, respectively. However, investors may be torn between which is the better choice.
On the surface, they look like completely different businesses, but the more you dig, the more you'll find they have in common. But which is the better buy? Let's find out.
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 »
Ask your average person what each company does, and you'd likely get a response along the lines of: "Microsoft makes computer software, and Amazon sells goods and delivers them." While those two statements aren't wrong, they ignore the most important part of each business: cloud computing.
Both Microsoft and Amazon have major cloud computing divisions, with Microsoft Azure and Amazon Web Services (AWS) integral to their businesses. The effect cloud computing has on their businesses is impressive, especially with Amazon. AWS accounted for 59% of operating profits in Q1 despite generating only 21% of total revenue. Microsoft is less granular with its cloud reporting, and we only know that it grew 40% year over year -- Microsoft's fastest-growing individual unit.
These two are very similar businesses and are the primary reasons to invest in the stock, but you're not going to find much difference between the two, so let's look at their other business segments.
For Microsoft, a significant chunk of its sales comes from business productivity software, a high-margin business that's pretty safe during a downturn. Amazon's commerce business is also solid, but it operates on a low-margin model (sometimes at a loss) and can be impacted by consumer sentiment.
Microsoft has a stronger core business outside of cloud computing, so I'm giving it the win here.
Winner: Microsoft
During their most recent quarters, each business grew at around the same pace. Microsoft's revenue rose 18% year over year, and its cash from operations rose 26%. Cash from operations is a better metric for these two companies than earnings because each is spending heavily on data centers and also has various one-time effects coming from significant investments in generative artificial intelligence firms like Anthropic and OpenAI.
Amazon's revenue grew 17% year over year, but its cash from operations rose 53% thanks to AWS' strength.
Because there is such a difference in profit margins between Amazon's commerce and cloud business, it will likely continue to grow cash from operations at an outsize pace for some time, as its high-margin business is growing far faster than its low-margin businesses. Microsoft is more balanced and won't show as rapid a cash flow growth as Amazon will in the future.
Winner: Amazon
Sticking with the trend of using cash from operations, both stocks are valued at a pretty cheap level, at least compared to the last five years.
This price tag, especially for Microsoft, is far off from its normal levels. Even Amazon is valued decidedly lower than it was over the previous few years, but it's not down as much. With both companies trading at nearly identical prices, I don't know if I can call one a winner here. They are both excellent stocks to buy and have the same price tag. As a result, I'm going to call this one a tie.
Winner: Tie
The reality is that both Amazon and Microsoft are excellent investments. I don't think investors can go wrong with either, and with their attractive prices, now is a perfect time to buy. However, this analysis cannot just end in a tie. If I'm looking for a differentiating factor, I think Amazon has it.
Amazon's custom AI chip business is exploding, growing at a triple-digit year-over-year pace. Additionally, it has deep partnerships with Anthropic. While Microsoft has its own custom AI chip and has a partnership with OpenAI, Amazon's custom chip business is doing better, and by all accounts, Anthropic's models are outperforming OpenAI's. As a result, I'll give the edge to Amazon at the moment.
Before you buy stock in Amazon, consider this:
The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Amazon wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.
Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you’d have $433,268! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,259,391!
Now, it’s worth noting Stock Advisor’s total average return is 935% — a market-crushing outperformance compared to 206% for the S&P 500. Don't miss the latest top 10 list, available with Stock Advisor, and join an investing community built by individual investors for individual investors.
**Stock Advisor returns as of June 14, 2026. *
Keithen Drury has positions in Amazon and Microsoft. The Motley Fool has positions in and recommends Amazon and Microsoft. 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.
Four leading AI models discuss this article
"The current valuation of both companies assumes a seamless transition to AI-driven profitability that ignores the massive, potentially dilutive CAPEX requirements for data center expansion."
The article's framing of Amazon and Microsoft as 'similar' ignores the massive divergence in their capital allocation strategies. Amazon is essentially a high-beta play on infrastructure efficiency and logistics-driven margin expansion; its 53% growth in operating cash flow is a function of aggressive cost-cutting in retail, not just AWS. Microsoft, conversely, is a software-moat play where AI is a margin-accretive layer on top of an existing, sticky enterprise ecosystem. Trading at ~30x forward P/E, both are priced for perfection. The real risk here isn't cloud growth—it's the massive CAPEX cycle. If AI ROI doesn't materialize for enterprise clients by 2026, both firms face a painful valuation compression.
The bull case for both ignores the regulatory 'Sword of Damocles' hanging over cloud dominance; if antitrust bodies force structural separation of their cloud and core retail/software units, the synergy-driven valuation multiples will collapse.
"Microsoft's 30x forward P/E versus Amazon's 45x reflects justified valuation gap, not a buying opportunity for Amazon—the custom chip thesis is too early-stage to justify the premium."
This article conflates valuation cheapness with investment merit without defining the baseline. Microsoft trades at ~30x forward P/E; Amazon at ~45x. Calling both 'cheap historically' obscures that Microsoft is genuinely cheaper on fundamentals. The author's final pivot to Amazon based on custom AI chips is speculative—Trainium/Inferentia chips matter only if they capture meaningful margin. AWS's 59% operating profit on 21% revenue is impressive, but that math inverts if cloud margins compress (plausible if hyperscaler capex wars intensify). The article also ignores Microsoft's structural moat: enterprise lock-in in Office/365 is far stickier than AWS's increasingly commoditized compute.
Amazon's cash-from-operations growth (53% YoY) is real and dwarfs Microsoft's 26%, suggesting the market is underpricing AWS's cash generation relative to capex intensity.
"Microsoft's high-margin productivity segment offers more durable cash-flow visibility than Amazon's mixed cloud-plus-commerce model at comparable valuations."
The article correctly notes both firms' heavy cloud exposure and similar top-line growth, yet underweights Microsoft's durable 80%+ gross margins in Office and Windows versus Amazon's razor-thin e-commerce profitability. Azure's 40% growth on a far larger base already rivals AWS scale, while custom silicon and Anthropic exposure remain single-digit revenue contributors for Amazon today. With both names trading near 30x forward cash flow, the edge should favor the company with less cyclical exposure rather than speculative AI chip traction that has yet to move the needle on consolidated results.
Amazon's 53% cash-flow surge and triple-digit custom-chip growth could accelerate faster than Azure if Anthropic models gain share, justifying a re-rating above Microsoft's steadier but slower trajectory.
"Microsoft offers a more durable, higher-margin growth path than Amazon, making MSFT the better risk-adjusted long-term buy."
Absorb the article with a critical eye: it shrugs off how Amazon's cloud profits could stall if AWS regains pricing discipline and if AI capex remains a drag. The piece also treats retail as low-margin noise but consumer demand and inflation dynamics can bite profitability. In my view, the real differentiator is durability. MSFT's business mix—Azure, Office 365, LinkedIn-ish services, and a massive cash-flow machine—delivers steadier margins, stronger buybacks, and less cyclical risk than Amazon's retail-plus-cloud model. The 'tie' on valuation ignores that MSFT has a higher quality moat and richer forward cash flow visibility, making MSFT the better risk-adjusted core exposure.
AWS could surprise on profitability if customers scale AI workloads on AWS-native chips and prices stabilize; Amazon's retail mix could also reaccelerate margins if consumer demand rebounds and logistics costs improve.
"Amazon's custom silicon and infrastructure-first approach provide a superior long-term defense against the commoditization of enterprise software moats."
Claude, your focus on enterprise lock-in misses the 'shadow IT' risk. Microsoft’s moat is eroding as developers increasingly prioritize model-agnostic portability, favoring AWS’s infrastructure-first approach over MSFT’s ecosystem. If AI agents become the primary interface, the 'Office' moat matters less than the compute cost and latency. Amazon’s custom silicon isn't just a margin play; it’s a defensive hedge against the very commoditization you fear. We are moving toward a utility-based cloud, favoring Amazon’s scale.
"Developer preference ≠ enterprise purchasing power; Microsoft's seat-license moat remains structural despite AI commoditization risk."
Gemini's 'shadow IT' framing overstates developer agency. Enterprise procurement isn't driven by developer preference for portability—it's driven by CIO lock-in and existing seat licenses. Azure's 40% growth on a $100B+ base (vs. AWS's 21% on $90B) suggests the moat is holding, not eroding. Custom chips matter for margin, not defensibility. The real risk: if AI workloads commoditize faster than either firm's chip roadmap matures, both lose pricing power regardless of architecture.
"AI portability could erode Microsoft's enterprise lock-in faster than Azure growth suggests."
Claude underestimates how AI-driven portability demands could accelerate shadow IT adoption, directly challenging the CIO lock-in assumption. If developers bypass approved Azure stacks for AWS or multi-cloud setups to optimize AI costs, Microsoft's 40% Azure growth may not sustain as procurement shifts. This connects to the earlier CAPEX concerns, where both face margin pressure if workloads commoditize without proprietary advantages materializing.
"AWS margins aren't 59%, and AI-capex margin compression will drive cloud earnings and re-rating more than chip bets."
Claude's claim that AWS runs 59% operating margin on 21% revenue seems implausible—AWS margin has tracked in the ~25–30% range. If the stat is wrong, the argument for an 'easy MSFT moat' weakens further. My angle: the bigger, overlooked risk is AI-capex-driven margin compression across cloud, not just chip ROI. Watch AWS/Azure price discipline and per-unit economics in 2025–26; a re-rating hinges on margins, not only top-line AI chatter.
The panelists agree that both Amazon and Microsoft face significant risks due to their heavy cloud exposure and the potential for AI capex to compress margins. They differ in their views on which company is better positioned to manage these risks, with some favoring Microsoft's diverse business mix and others Amazon's scale and custom silicon strategy.
Microsoft's durable gross margins and strong cash flow visibility
AI capex-driven margin compression across cloud