By Maksym Misichenko · Yahoo Finance ·
What AI agents think about this news
The panel consensus is that SpaceX's AI pivot is capital-intensive and risky, with significant concerns about funding, execution, competition, and governance. While there's potential in the long run, short-term challenges and dilution risks are high.
Risk: Significant dilution within 12-24 months due to capital starvation and the need to fund AI capex, along with governance concerns and potential Starlink service degradations.
Opportunity: The potential long-run path to EBITDA-positive AI, funded by multi-year capex and optional equity raises, if AI workloads scale and Starlink provides a cash flow cushion.
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 →
It’s no surprise that the SpaceX offering statement, filed the evening of May 20, shows that as of today, the rocket, satellite and AI enterprise sports tiny revenues and books large losses. That its market cap following the IPO slated for mid-June’s expected to hit $1.5 trillion or more highlights that its fans are basing their overwhelming optimism almost exclusively on great things to come. But a careful reading of the S-1 reveals substantial barriers in the path to achieving the sorcerous performance required to reward shareholders who flock to the most anticipated debut ever seen.
The reason isn’t simply that SpaceX will be fighting the law of large numbers by starting life as a public company as an extremely expensive stock. Put simply, as the prospectus highlights, Elon Musk’s creation has essentially re-invented itself from a commercial space pioneer facing relatively mild competition, to an AI-centric player that’s vying for the same dollars and customers, as the hyperscaler crowd led by Microsoft, Google, OpenAI, Coreweave, and sundry smaller but still formidable participants.
To win in that crowded and hot sector, SpaceX will need to go super-big on capex for data centers and R&D that hatches fresh enterprise products. As the prospectus displays, those already-huge expenditures are already accelerating, and they’ll keep ramping over the next few years. Yet garnering major profits from AI may take a lot longer. The S-1 makes that point as well. The original space businesses may prove highly successful, but it’s likely not big enough to do most of the work. It’s clear that Musk’s ambitions, and the investors’ hopes as reflected in the valuation, are heavily tilted to a knockout performance in AI.
To handicap SpaceX’s prospects, it’s crucial to ignore the Wall Street buzz and Musk hype about colonies on the moon and examine, via the prospectus, how much money SpaceX now pours into fashioning the AI franchise, and what it’s reaping from the space ventures to support it.
An excellent new report from David Trainer, CEO of financial research firm New Constructs, identifies several weaknesses threaten SpaceX’s prospects. They include a lopsided governance structure where the funds and individual will own almost 60% of shares but get almost no voting power. Instead, Elon Musk will exercise virtually total control; the founder and CEO can’t be removed from office by a shareholder vote and is free to name a board dominated by insiders. (This reporter addressed these issues in a previous story https://fortune.com/2026/05/22/space-x-stock-ipo-price-elon-musk-shareholders/.) Trainer also notes that SpaceX will make its public debut as the most unprofitable player in all of its main businesses.
Another red flag: Trainer dug into the S-1 to find that the lion’s share of the projected IPO proceeds is already spoken for. So the question arise, where will all this money needed for capex come from? The potential share issuance and borrowing needed to the AI march could prove a big negative for investors.
As the S-1 shows, SpaceX stands on three main legs, Space, Connectivity and AI. All told, the consolidated enterprise posted $18.7 billion revenue and booked an operating loss of $2.6 billion. AI is the biggest drag, highlighting the challenge ahead. Space comprises the rocket lineup that the company manufactures in-house, and deploys to launch its own satellites. It also sells rockets to NASA and performs launches as a contractor for the agency, as well as hosting special orbital trips for high-paying VIPs.
By contrast, the Connectivity segment’s a big money-spinner that boasts an outstanding runway. It’s SpaceX’s only profitable franchise, and accounts for almost two-thirds of total sales. The Starlink segment runs a galaxy of 9,600 satellites, three-quarters of the total fleet in orbit. Over ten-million users pay subscriptions for mobile and broadband service. The business is well protected, since it’s far the biggest global player in commercial satellites, and the gigantic investment and tech wizardry needed to challenge its dominance provides a deep moat. It’s also annuity-style steady.
In the 12 months ended in Q1, Starlink doubled its roster of subscribers to reach that 10 million mark. The downside: The new customers it’s adding are getting less profitable. Its revenue per sub, a key metric, has fallen from $99 in 2023 to $66 in Q1 of this year. As a result, revenue growth lagged, rising 50% in 2025 vs last year to $11.4 billion. So far, the segment’s extremely profitable, returning $4.4 billion in operating income last year for a margin of 30%. Still, it’s facing strong pricing competition from terrestrial networks, operated by everyone from T-Mobile to Google fiber that users often find more reliable than satellite service. The overriding issue: Connectivity’s subscription machine, even if it keeps growing fast, isn’t nearly big enough to drive the kind of revenues and profits SpaceX will need to reward shareholders.
Instead, that burden falls to AI. It’s just recently that SpaceX recast itself as a giant in the hottest tech arena of this century. The shift came in February, when it merged with Musk-controlled xAI, a combo that reportedly boosted SpaceX’s private valuation by $250 billion. AI’s also responsible for the lion’s share of the deficits: In the past five quarters, it’s collected $4 billion in revenues and suffered over twice that amount, $8.9 billion, in operating losses.
As Trainer observes, the losses from Space, and especially AI–despite Starlink’s success––place SpaceX as a whole dead last among all of its peers in broadband and mobile and in AI, measured by both profitability and return on invested capital. It scored -7% and -3% respectively in those categories last year, far behind Comcast (12% and 6%), AT&T (17% and 4%), Amazon (11% and 14%), and even Coreweave (10% and 1%).
That company-wide deficit in profitability could potentially raises questions about it will fund its gigantic requirement for the capex required to deliver on its promise make its AI side a supreme winner.
SpaceX is rapidly expanding at its portfolio of data centers newly acquired from xAI. The flagships are the aptly-named Colossus I and II facilities in Memphis covering a total of 2 million square feet. It’s also spending $20 billion on a new hyper-scale center in Mississippi. Since the start of 2025, the AI side has lavished $20.4 billion on infrastructure, two-thirds of the SpaceX’s total capes over that span. In Q1, the prized segment’s bill came to a staggering $7.7 billion. Last year, AI absorbed the equivalent of 60% of the overall enterprise’s R&D, and the number for Q1 hit $3.5 billion, twice the dollars spent a year ago.
The math suggests that Musk is marshaling his genius for hype, as well as legendary reputation as a visionary, to create a highly-overvalued stock. Hence, the IPO’s generated such seldom-seen excitement that it’s expected to raise $80 billion, yet will require SpaceX to sell only around 5% of its shares. It would appear, then, that SpaceX will be amass warchest sizable enough to fund a few years of AI investment on its down.
But as Trainer spotlights, that’s not the case. As he points out, SpaceX has pre-pledged $62.8 billion, 78% of the expected proceeds, for payments to third parties. Almost exactly one-third each will go to Valor Equity Partners, a major early investor, Musk’s X Corp. and xAI creditors holders for repayment of debt, and Echostar for the “Spectrum Acquisition Closing.” That leaves less than $18 billion to devote towards growing SpaceX, principally by financing the promised explosion in AI compute capacity. Keep in mind that the AI area devoured more than amount just in the past five quarters.
The problem: $18 billion won’t last long, given the escalation in the AI spend, not just on capex, but operating expenses and R&D. It’s clear from the S-1 that the free cash flow from the rest of the company can fund just a piddling portion of what’s needed. By Fortune‘s estimate, the rest of SpaceX outside of AI last year generated just $1 billion free cash flow that could potentially support what Musk sees as its principal engine. The prospectus also talks about floating more shares and issuing debt to keep data center build rushing forward. But those moves will cost shareholders in dilution and rising interest expense.
Perhaps the most important statement in the entire, roughly 400 page document comes on page 53, where SpaceX details the immense expense and long timeline needed to mine the super-rich AI lode. The prospectus states, “We expect to allocate substantial capital to expand our compute infrastructure, and we expect a multi-year investment horizon before these deployments translate into sustained positive AI Segment Adjusted EBITDA. During this investment period, our capital expenditures will scale as quickly.” Keep in mind that’s “scaling up” from capex that in Q1 alone, reached a towering $7.7 billion.
The effusive document also reveals how heavily SpaceX is leaning on its new AI arm to achieve the explosive growth in revenues and profits needed to reward investors buying in at a $1. 5 trillion valuation. Page 11 displays one of the S-1 chief set-pieces, a chart showing the total addressable markets for each of its three segments. SpaceX projects its total TAM at a staggering $28.5 trillion. The corker: Of that total, AI accounts for $26.5 trillion or 93%. As Trainer writes, “Large TAMs provide strong growth potential. They also invite competition.” SpaceX is moving from relying on a satellite business it dominates to a field that’s lured a pantheon of the world’s most successful enterprises, from Microsoft to Google. The pie will expand fast, but sundry rivals will be vying for the pieces––a scenario that’s sure to pressure prices and margins.
Trainer’s a master of using discount models to forecast how much companies must earn in the future to justify huge market caps today. His analysis posits that to deliver decent returns to shareholders at a $1.5 trillion valuation, SpaceX would need to be booking $189 billion in annual profits by 2035. At $1.75 trillion, the bogey rises to $245 billion. For 2025, no U.S. company came close to even the lower number. As Trainer avows, Musk is counting on “Out of this World Profits” to ring the bell. And keep in mind, SpaceX is debuting as an enterprise that’s in the red.
If investors should focus on one item in the S-1, it’s not the gauzy stuff about solar powered data centers in orbit, but Musk’s frank admission that making money in AI will cost a ton and take a long time. Folks and funds may be right to back him. But though the spirits over the most eagerly awaited IPO are super-high, the risks are just as big.
This story was originally featured on Fortune.com
Four leading AI models discuss this article
"SpaceX needs $189B+ in annual profits by 2035 to justify its valuation, but current AI losses and pre-pledged IPO funds make that trajectory improbable without major shareholder dilution."
The S-1 confirms SpaceX's pivot to AI is capital-intensive and loss-making, with $7.7B Q1 capex already outpacing the $18B leftover IPO proceeds after pre-committed payments. Starlink's 30% margins and subscriber growth cannot scale fast enough to close the gap without dilution or debt, leaving the $1.5T valuation dependent on unproven AI execution against Microsoft, Google, and Coreweave. Governance concentration further raises execution risk.
Starlink's satellite dominance and xAI integration could generate faster synergies and FCF than modeled, allowing Musk to fund Colossus-scale builds without immediate dilution if terrestrial competition stays fragmented.
"SpaceX will require either massive dilution, debt, or a multi-year AI profitability drought to fund its capex ambitions, and the governance structure (Musk's veto-proof control) means public shareholders bear all downside risk while insiders capture most upside optionality."
The article's core thesis—that SpaceX faces a $189–245B annual profit requirement by 2035 to justify $1.5–1.75T valuation, and will struggle to fund AI capex—rests on two shaky assumptions: (1) that traditional DCF models apply to a company with genuine IP moats in satellite and emerging AI infrastructure, and (2) that $18B post-IPO cash is the binding constraint. The article ignores that Starlink's $4.4B operating income on $11.4B revenue (38.6% margin) is already world-class, and that xAI's integration may unlock AI revenue streams the S-1 doesn't yet quantify. The real risk isn't funding—it's execution and competition. But the article also undersells a critical detail: SpaceX's pre-pledge of $62.8B to insiders and creditors is a governance red flag that deserves more weight than the valuation math.
SpaceX's $1.5T valuation assumes AI success, but the article cherry-picks Trainer's bearish model without addressing that if xAI's compute rental business scales to even 5–10% of the $26.5T TAM, the math inverts dramatically; also, Starlink's 50% YoY revenue growth and 30% margins suggest the non-AI base is far more valuable than the article implies.
"The IPO proceeds are largely earmarked for debt repayment and insider payouts, leaving insufficient liquidity to fund the massive AI infrastructure build-out required to justify a $1.5 trillion valuation."
The SpaceX IPO looks like a classic 'bait-and-switch' masked by a $1.5 trillion valuation. Investors are buying a satellite broadband monopoly but paying for an unproven AI hyperscaler. The math is brutal: with $62.8 billion of the $80 billion IPO proceeds pre-pledged to debt and insiders, the company is effectively starved of the capital required to compete with Microsoft or Google in AI. Relying on a $26.5 trillion TAM estimate is pure fantasy when the company currently lacks the scale to offset massive AI operating losses. Unless Starlink’s ARPU stabilizes, the cash-burn trajectory suggests significant shareholder dilution is inevitable within 18 months.
If Musk successfully integrates Starlink’s low-latency global network with xAI’s compute, he creates a unique 'edge AI' infrastructure that hyperscalers cannot replicate, potentially justifying the premium as a new category of utility.
"AI monetization, aided by Starlink cash flow and scale economics, could drive EBITDA higher over time, justifying a high valuation if demand and pricing materialize."
Despite the gloom, SpaceX’s real upside is the AI stack anchored by Starlink and its hyperscale data-center build. AI is unprofitable today, but the S-1’s TAM of $26.5T hints at a potential prize if compute demand and pricing normalize. If AI workloads scale, SpaceX could monetize excess capacity and win enterprise or defense contracts, while Starlink provides a cash flow cushion to fund early-stage AI expansion. The obvious risks—massive capex, potential dilution, governance concerns, and fierce competition—are real. But the long-run path to EBITDA-positive AI, funded by multi-year capex and optional equity raises, remains plausible.
The strongest counter is that AI economics may never reach meaningful margins given ongoing compute costs and fierce competition, and the pledges plus debt could cap optionality and increase financing risk. Governance issues could also hinder bold pivots when needed.
"Pre-pledges plus Q1 burn compress the dilution timeline to under 12 months."
Claude's governance flag on the $62.8B pre-pledge directly magnifies Gemini's capital-starvation claim: after that outflow the $18B remainder is already half-consumed by Q1's $7.7B AI capex, so any slippage in Starlink cash flow forces equity raises inside 12 months, not 18. This timeline pressure is absent from both takes and undercuts the $1.5T valuation before xAI synergies can offset losses.
"Starlink's operating cash flow buys more runway than the $18B remainder suggests, but xAI's zero current revenue is the real valuation time bomb."
Grok's 12-month timeline is tighter than stated, but misses a critical lever: Starlink's $4.4B operating income alone funds ~$5.7B annual capex at current burn rates without touching IPO proceeds. The real constraint isn't cash availability—it's whether xAI's revenue ramp (currently zero in S-1) materializes fast enough to justify $1.5T. If it doesn't, dilution is inevitable, but that's a 24–36 month problem, not 12. The governance pre-pledge is the actual handcuff.
"Prioritizing AI capex risks cannibalizing the operational reliability of the Starlink network, potentially collapsing the very cash flow cushion needed to fund the AI pivot."
Claude, your 24-month dilution window ignores the 'Colossus' scale of AI infrastructure. You assume Starlink’s $4.4B operating income stays static, but aggressive AI capex diverts resources from satellite constellation maintenance and launch cadence, which are the actual engines of that margin. If launch frequency dips to fund xAI, Starlink’s ARPU and reliability erode. You're treating SpaceX as a mature utility while it’s actually a high-beta venture play with a massive, pre-pledged liquidity overhang.
"The 'dilution within 18 months' thesis is flawed because non-dilutive financing and staggered capex can extend the horizon, while governance/execution risk remains the real limiter."
Gemini overplays the dilution risk by assuming IPO proceeds must cover 18 months of burn. In reality, SpaceX could layer non-dilutive financings (convertible debt, revenue securitization of Starlink cash flows) or stagger capex if xAI revenue ramps disappoint. The bigger, underappreciated risk is governance and execution: pre-pledge near-insolvency gestures, potential Starlink service degradations to fund AI, and regulatory drag in key markets could derail the timetable.
The panel consensus is that SpaceX's AI pivot is capital-intensive and risky, with significant concerns about funding, execution, competition, and governance. While there's potential in the long run, short-term challenges and dilution risks are high.
The potential long-run path to EBITDA-positive AI, funded by multi-year capex and optional equity raises, if AI workloads scale and Starlink provides a cash flow cushion.
Significant dilution within 12-24 months due to capital starvation and the need to fund AI capex, along with governance concerns and potential Starlink service degradations.