By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panelists generally agree that SpaceX's $2.1T valuation is overly optimistic, hinging on perfect execution across multiple capital-intensive, regulated businesses. They highlight the extreme forward P/S ratio, reliance on unconfirmed AI deals, and potential risks in the space and connectivity segments.
Risk: The extreme reliance on unconfirmed AI deals and the potential evaporation of revenue if customers build in-house capacity or negotiate down pricing.
Opportunity: The potential structural cost advantage from Starship's projected sub-$10/kg launch costs, enabling AI racks in perpetual sunlight without terrestrial grid or cooling constraints.
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 (NASDAQ: SPCX) went public on Friday, June 12, and ended the day with a 19% gain. The company had a market capitalization of $2.1 trillion at the close of trading, making it the world's seventh-most-valuable company.
While SpaceX is best known for developing the world's first reusable rockets, management believes space-related solutions actually represent its smallest financial opportunity in the long run. Instead, the company could make most of its money by selling connectivity and artificial intelligence (AI) solutions, and it's already having commercial success on both fronts.
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 »
That said, SpaceX is still generating very little revenue relative to its enormous market capitalization, which I think creates an uncomfortable risk-versus-reward situation for investors. Here's why I'm not buying the stock.
SpaceX divides its business into three core segments:
SpaceX values its addressable market in the space segment at $370 billion, whereas the connectivity business presents a $1.6 trillion opportunity. But the AI business dwarfs both, with a potential market size of $26.5 trillion.
SpaceX is already responsible for more than 80% of the world's mass to orbit in the space business, meaning it's launching more commercial payloads than any other company or government, and it isn't even close. This market share will only grow as Starship is used more frequently, because it has a payload capacity of 100 metric tons, more than four times the capacity of Falcon 9.
On the connectivity side, there's SpaceX with its fleet of satellites. The company will start launching its V3 satellites later this year, which will offer more than 10 times the bandwidth of the current V2 generation. Plus, Starship will launch up to 60 V3 satellites into orbit at a time, whereas Falcon 9 has a capacity of just 27.
Finally, the AI business currently draws most of its revenue from Grok subscriptions and from renting spare data center capacity to other companies. When SpaceX bought xAI, it acquired data centers, including Colossus and Colossus II, which house hundreds of thousands of graphics processing units (GPUs) from suppliers including Nvidia.
In the future, SpaceX believes it can host AI computing clusters in space, where they can run on solar power with no need for complex liquid cooling systems, which waste a lot of water. Data would be beamed back to Earth via Starlink satellites, giving SpaceX a huge competitive advantage over every other AI infrastructure company.
SpaceX generated $18.7 billion in total revenue during 2025, up 33% from the previous year. Here's how it was broken down:
| Business Segment | Revenue | Year-Over-Year Growth | |---|---|---| | Space | $4.1 Billion | 8% | | Connectivity | $11.4 Billion | 50% | | AI | $3.2 Billion | 22% |
Connectivity was not only the largest but also the fastest-growing business last year. But that could soon change, because SpaceX has an active deal to rent $1.25 billion worth of computing capacity per month to Anthropic, and another deal to rent $920 million worth of capacity per month to Alphabet starting in October. In other words, the AI business could soon have $26 billion in annualized revenue from two customers alone.
As a result, Wall Street thinks SpaceX could generate as much as $64.5 billion in total revenue during 2027 (according to Yahoo! Finance), more than triple its 2025 result. While that sounds promising, it would still give SpaceX stock a sky-high forward price-to-sales (P/S) ratio of 32.5.
For context, the Nasdaq-100 technology index trades at a P/S ratio of 6.8 today, which is near a record high. That suggests SpaceX might be heavily overvalued relative to a basket of its big-tech peers.
As a result, while the SpaceX story is certainly positive, its valuation assumes perfect execution. Even if the company meets Wall Street's lofty 2027 revenue forecast, its stock would still be relatively expensive, which could limit further upside. If the company generates less revenue than expected next year, the stock could suffer a sharp correction. That doesn't sound like an attractive risk-versus-reward proposition, so I'm not a buyer right now.
Before you buy stock in Space Exploration Technologies, 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 Space Exploration Technologies 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 207% 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 15, 2026. *
Anthony Di Pizio has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Alphabet 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.
Four leading AI models discuss this article
"A $2.1 trillion market cap prices in perfection, ignoring the extreme capital expenditure risks and margin compression inherent in pivoting a launch company into a commodity AI compute provider."
The $2.1 trillion valuation at IPO is a massive red flag. A 32.5x forward price-to-sales ratio assumes SpaceX executes perfectly on AI infrastructure and connectivity while maintaining its launch monopoly. The article highlights $26 billion in potential annualized AI revenue from Anthropic and Alphabet, but this relies on the assumption that SpaceX can sustain these massive compute rentals without cannibalizing its own margins or facing intense competition from hyperscalers like AWS or Azure. At this scale, SpaceX is priced as a mature tech giant, not a growth-stage space firm. The valuation leaves zero margin for error in a capital-intensive industry prone to regulatory and technical delays.
If SpaceX successfully achieves orbital AI computing, they effectively bypass terrestrial energy and cooling constraints, creating a proprietary moat that justifies a premium valuation far exceeding traditional data center providers.
"SpaceX's valuation is a binary bet on AI rental revenue from two customers, not a diversified growth story—a single renegotiation or in-house pivot by either customer could halve the bull case."
SpaceX's $2.1T valuation hinges entirely on the AI business scaling from $3.2B (2025) to ~$26B annualized revenue by late 2026—a 700%+ jump dependent on two customers (Anthropic, Alphabet). The article correctly flags the 32.5x forward P/S as extreme, but undersells a critical risk: those $1.25B/month and $920M/month deals are *rental* agreements, not equity stakes. If either customer builds in-house capacity or negotiates down pricing (standard in infrastructure), revenue evaporates fast. The space business (80% of orbital mass) grows only 8% YoY—mature, competitive, margin-pressured. Connectivity at 50% growth is real, but Starlink faces regulatory headwinds (FCC spectrum, international licensing) the article omits. The 'AI in space' thesis is speculative; no revenue yet.
If Anthropic and Alphabet deals hold and scale as promised, SpaceX's AI segment alone justifies a $500B+ valuation within 24 months, making current pricing a bargain for long-dated holders willing to tolerate execution risk.
"SpaceX's reported valuation already prices in perfect delivery of unproven AI orbital infrastructure that current financials do not support."
The article's core claim rests on a false premise: SpaceX has not gone public and trades under no ticker like SPCX. Treating 2025 revenue of $18.7B and a $2.1T debut valuation as settled fact ignores that any IPO would face intense regulatory, disclosure, and dilution scrutiny absent today. Even granting the three-segment model, the 32.5x 2027 P/S assumes flawless execution on Starship cadence, V3 bandwidth, and $26B AI deals that have no public confirmation. Connectivity growth at 50% is real via Starlink but remains capital-intensive with uncertain margins once subsidies fade.
If SpaceX does IPO at scale, the AI data-center-in-orbit thesis could justify re-rating above peers if solar-powered clusters deliver measurable cost advantages by 2028, rendering today's forward multiples irrelevant.
"The valuation prices in near-perfect execution across three capital-intensive, regulatory-heavy businesses, creating outsized downside risk if any revenue line underperforms."
SpaceX's IPO narrative hinges on three revenue engines—Space, Connectivity, and AI—yet the valuation looks like a bet on near-perfect execution across three capital-intensive, regulated businesses. Even with 2025 revenue of $18.7B and a 2027 consensus around $64B, a $2.1T market cap implies roughly 32x forward P/S, demanding margin expansion and sustained pricing power unlikely in a cyclical, hardware-heavy space. The article glosses over risks: Starship/Falcon cost and certification timelines, satellite capex and Starlink deployment cadence, and AI revenue concentration with Anthropic/Alphabet. Questionable claims (e.g., >80% of world mass to orbit) warrant scrutiny. If any leg underperforms, downside could be outsized.
Bull case: SpaceX's Starlink network effects and xAI-driven compute demand could create a durable moat and cloud-scale economics, potentially re-rating the stock well before 2027 if contracts scale and margins improve.
"SpaceX's vertical integration creates a cost-per-bit advantage that renders the 'rental risk' moot by making them the only viable low-latency compute provider."
Grok correctly identifies the 'phantom IPO' problem, but misses the second-order effect: the $2.1T valuation acts as a signaling mechanism for private secondary markets. This isn't just about retail hype; it’s about institutional liquidity pricing in a 'monopoly premium.' Claude’s focus on rental risk is vital, but ignores that SpaceX's vertical integration—building the launch vehicle, the satellite, and the compute rack—creates a cost-per-bit floor no hyperscaler can match, effectively forcing Anthropic into a permanent lock-in.
"Vertical integration is a cost advantage only if demand stays locked; it becomes a liability if customers defect or build alternatives."
Gemini's 'cost-per-bit floor' lock-in thesis assumes SpaceX's vertical integration yields structural advantages over hyperscalers' purchasing power and terrestrial alternatives. But this ignores: (1) AWS/Azure can build competing satellite networks—they have capital; (2) rental agreements are renegotiable every 24–36 months; (3) 'permanent lock-in' in infrastructure is fantasy once customers achieve technical parity. Vertical integration cuts both ways—it's also capex-intensive inflexibility if demand shifts.
"Starship economics could create an orbital cost moat that survives contract cycles and undercuts hyperscaler alternatives."
Claude's critique of vertical integration overlooks Starship's projected sub-$10/kg launch costs by 2027, which would let SpaceX site power-hungry AI racks in perpetual sunlight without terrestrial grid or cooling constraints. That structural cost edge survives contract renegotiations and makes in-house satellite builds by AWS far less economical than Claude assumes. The real risk is whether Starship cadence actually materializes on schedule.
"Even with scale in Anthropic/Alphabet deals, the moat hinges on durable margins and timing that could be eroded by renegotiations and regulatory delays, threatening the AI-revenue ramp."
Claude flags rental risk and concentration, which is valid. My counter: even if Anthropic/Alphabet deals scale, the real lever is the path to durable margins under regulatory scrutiny and potential hyperscaler counter-moves. The second-order risk you’re missing is that if AI compute demand fails to materialize or pricing renegotiations bite, the supposed moat from vertical integration collapses. Regulatory/licensing delays for Starlink could also throttle the AI ramp and capital cadence.
The panelists generally agree that SpaceX's $2.1T valuation is overly optimistic, hinging on perfect execution across multiple capital-intensive, regulated businesses. They highlight the extreme forward P/S ratio, reliance on unconfirmed AI deals, and potential risks in the space and connectivity segments.
The potential structural cost advantage from Starship's projected sub-$10/kg launch costs, enabling AI racks in perpetual sunlight without terrestrial grid or cooling constraints.
The extreme reliance on unconfirmed AI deals and the potential evaporation of revenue if customers build in-house capacity or negotiate down pricing.