By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel consensus is bearish, with the key risk being the high capex intensity and cash burn of xAI, and the potential for Starlink's ARPU to stall against competition.
Risk: High capex intensity and cash burn of xAI
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 →
SpaceX operates some great businesses, notably its low-Earth-orbit satellite internet business Starlink.
However, the company's artificial intelligence unit is capital-intensive and losing billions of dollars.
Analysts at Morningstar think investors will be able to buy SpaceX stock at a cheaper price down the line.
Ever since SpaceX released its registration statement, revealing key financials, investors have gone back and forth about the company’s valuation, which media outlets expect to be in the range of $1.75 trillion to $2 trillion.
Now, one Wall Street analyst is suggesting that the company’s initial public offering significantly overvalues the company.
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 »
In a recent research note, Morningstar analyst Nicolas Owens said his team thinks the company is only worth about $780 billion, implying a 55% lower valuation from $1.75 trillion.
Here’s why.
Earlier this year, SpaceX acquired Elon Musk’s artificial intelligence company, xAI, which owns the Grok AI digital assistant and social media platform X. Musk is also the founder and CEO of SpaceX.
XAI also owns and operates data centers. This could be an advantage down the line because it will not rely on third-party data center companies.
Image source: Getty Images.
However, right now it’s a difficult business to run. The unit generated $818 million of revenue in the first quarter of 2026 and an operating loss of nearly $2.5 billion.
In 2025, the unit generated $3.2 billion of revenue and an operating loss of nearly $6.4 billion.
Furthermore, the AI unit is quite capital-intensive. Roughly $12.7 billion of capital expenditures were devoted to the AI unit in 2025, and already $7.7 billion in the first quarter of 2026.
Owens and his team found xAI’s “economic moat indeterminate” and think it presents a “material threat of value destruction…”
Now, the good news for investors early on is that SpaceX is expected to be quickly added to most major market indexes within weeks of its trading debut.
The company could also be added to the broader benchmark S&P 500 just six months after going public.
This will force every fund tracking such indexes to buy SpaceX stock. Morningstar believes this will help support the stock and even potentially allow it to rise in the near term.
However, it is after these mechanical maneuvers that the stock will face a more uphill battle.
“We think the company has been significantly overvalued and investors will have opportunities to buy the stock at more attractive levels after the IPO,” Owens wrote.
Using a discounted cash flow analysis, Owens and his team estimate that SpaceX’s Starlink satellite internet business and its launch business are worth roughly $611 billion in enterprise value.
They assigned the AI business an additional $170 billion enterprise value in “probability-weighted scenarios.”
SpaceX is an impressive company, particularly with Starlink, its low-Earth-orbit satellite internet business that has a considerable lead in the sector, and its financials.
The company is asking for a high valuation, especially given xAI’s drag on the business. Now, SpaceX may very well get away with it, considering Musk’s cult-like following and hype around the IPO.
SpaceX will also have support from all the projected index inclusions. However, I think investors who buy the stock in the beginning will be operating in the Wild West.
I agree with Owens that there is a good chance the stock will be cheaper down the line, likely six months after its IPO, when all index inclusions have occurred, and lock-up provisions have expired.
Furthermore, waiting will give investors time to see SpaceX report a few quarters of earnings results, so I think investors are best off staying on the sidelines for the IPO.
When our analyst team has a stock tip, it can pay to listen. After all, Stock Advisor’s total average return is 983%* — a market-crushing outperformance compared to 212% for the S&P 500.
They just revealed what they believe are the 10 best stocks for investors to buy right now, available when you join Stock Advisor.
**Stock Advisor returns as of June 3, 2026. *
Bram Berkowitz has no position in any of the stocks mentioned. The Motley Fool has no position in any of the stocks mentioned. 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 bear case is valid today, but SpaceX’s large optionality in Starlink monetization and xAI licensing means the stock could still re-rate higher if any of those avenues materialize, making the valuation gap not a guaranteed downside."
Despite the headline overvaluation, the Morningstar take hinges on a narrow view of SpaceX’s cash flows. The article understates optionality: Starlink monetization could lift ARPU in more geographies and services, SpaceX’s launch cadence may secure more lucrative government/commercial contracts, and xAI could find profitable enterprise/licensing avenues even if current losses persist. Index inclusion risk is real, but near-term price support from buyers chasing a reduced-duration IPO bet could cap downside. The real risk to the bears is that any meaningful monetization of Starlink or licensing upside for xAI could compress downside and/or lift sentiment faster than the headline valuation implies.
Bullish counterpoint: if Starlink expands revenue and xAI begins generating licensing/enterprise upside sooner than expected, the optionality could justify a premium and prevent a sharp re-rating downside. The index/inclusion dynamics also provide near-term price support that the article downplays.
"The inclusion of xAI into the SpaceX corporate structure introduces a high-risk capital drain that fundamentally undermines the valuation of its stable aerospace and satellite internet businesses."
The article conflates SpaceX’s core aerospace dominance with a speculative, capital-heavy AI integration. Valuing SpaceX at $1.75 trillion requires assigning massive weight to Starlink’s terminal growth and launch monopoly, while the $170 billion assigned to xAI by Morningstar feels like a 'plug' figure to justify the valuation. The real risk isn't just xAI's cash burn; it's the governance risk of Musk using SpaceX as a balance sheet for his other ventures. If SpaceX goes public, the institutional 'forced buying' from index inclusion will provide a temporary floor, but the disconnect between aerospace cash flow and AI-driven capex will likely trigger a valuation reset once the initial hype fades.
If xAI achieves AGI, its integration into Starlink and autonomous launch systems could create a vertical monopoly that renders traditional DCF analysis obsolete by orders of magnitude.
"The $780B bear case undervalues xAI's capex-to-moat conversion potential, but Starlink's $611B slice is itself vulnerable to competitive margin compression that the article doesn't stress-test."
The article's $780B valuation hinges on a DCF that assigns xAI only $170B despite $12.7B capex in 2025 alone. That's a 13.3% implied return on deployed capital—absurdly low for an AI infrastructure play if xAI achieves even modest utilization gains. Morningstar's 'indeterminate moat' judgment is defensible but premature; xAI's vertically integrated data center + model stack could compound advantages faster than legacy cloud providers. The real risk isn't overvaluation per se—it's that Starlink's $611B valuation assumes stable margins while competition (Amazon, OneWeb) ramps. Index inclusion mechanics are real but temporary; the article correctly flags this as a 6-month tailwind, not a fundamental.
If xAI's $2.5B Q1 2026 loss reflects startup scaling (not structural failure), and capex eventually drives sub-$0.10/unit inference costs, the $170B placeholder could be a 10-bagger. Morningstar's framework may systematically undervalue optionality in AI infrastructure.
"SpaceX's IPO at $1.75T embeds unrealistic assumptions on xAI profitability given its current $2.5B quarterly losses."
Morningstar's $780B fair value for SpaceX rests on a $611B enterprise value for Starlink and launches plus only $170B probability-weighted for xAI. The AI unit's 2025 results—$3.2B revenue against $6.4B operating loss and $12.7B capex—show a capital sink that could widen if data-center buildouts accelerate. Index-driven buying may create a brief post-IPO lift, but six-month lock-up expirations and first earnings prints will expose whether Starlink's subscriber growth can offset xAI's cash burn. This setup favors waiting rather than chasing the $1.75T headline valuation.
Starlink could reach 20M+ subscribers by 2028 with higher ARPU from enterprise and government contracts, pushing its standalone value well above the $611B DCF and making today's multiple look conservative rather than excessive.
"Regulatory risk and margin compression from Starlink/AI capex are the real tests that could derail the xAI valuation, not just potential ROIC on paper."
Claude’s take rests on the premise that xAI’s capex will someday yield outsized returns; I’d push back that the real risk is structure, not scalability. The 13.3% implied ROIC point is not inherently absurd if you assume aggressive licensing and scale, but it ignores regulatory/antitrust headwinds and potential margin compression as Starlink faces competition and capex intensity remains high. Until governance, pricing power, and back-end costs stabilize, a material re-rating risk remains.
"The conflation of SpaceX and xAI introduces a governance discount that will outweigh any potential AI-driven upside."
Claude and Grok are missing the primary systemic risk: the 'Key Man' discount. SpaceX’s valuation is predicated on Elon Musk’s singular ability to execute, yet the cross-pollination between SpaceX and xAI creates a massive conflict of interest. If institutional investors view SpaceX as a vehicle to subsidize xAI’s capital-intensive AI ambitions, the valuation will not just reset—it will collapse under governance scrutiny. The market won't price this as a tech stock; it will price it as a conglomerate with opaque capital allocation.
"Governance risk is real but secondary to near-term cash burn visibility—the IPO honeymoon ends at first earnings, not at index inclusion."
Gemini's governance collapse thesis assumes institutional buyers care about Key Man risk at IPO—they don't, not yet. The real pressure point is Q1 2026 earnings: if xAI's $6.4B operating loss widens despite $12.7B capex deployment, and Starlink's ARPU stalls against Amazon competition, then the conglomerate discount Gemini flags becomes priced in fast. Until then, index flows mask the structural problem. That's the 6-month window Grok identified.
"Post-IPO earnings will expose xAI subsidization faster than Claude allows, accelerating Gemini's governance discount."
Claude underplays how xAI's $12.7B 2025 capex and widening losses will surface governance conflicts immediately in post-IPO filings. Institutions may tolerate Key Man risk at listing, but Starlink cash flows subsidizing Musk's AI bets will trigger proxy fights and multiple compression once Q1 2026 numbers reveal allocation opacity. Gemini's point lands harder once earnings mechanics are layered in.
The panel consensus is bearish, with the key risk being the high capex intensity and cash burn of xAI, and the potential for Starlink's ARPU to stall against competition.
High capex intensity and cash burn of xAI