By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
Nvidia's near-term revenue is secured via Google and Anthropic deals, but long-term sustainability is uncertain due to SpaceX's plans to design its own chips and the potential for hyperscalers to pivot to internal silicon once volumes justify it.
Risk: SpaceX's plans to design its own chips and the potential for hyperscalers to pivot to internal silicon once volumes justify it.
Opportunity: Near-term revenue from Google and Anthropic deals.
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 →
In the weeks ahead of its June 12 initial public offering, SpaceX racked up a couple of big deals to rent out parts of its data center capacity; one with artificial intelligence (AI) start-up Anthropic and one with Alphabet-owned Google. Both agreements will help SpaceX offset its AI infrastructure costs with recurring revenue streams.
In the background, however, these deals highlighted the AI industry dominance of another company: Nvidia (NASDAQ: NVDA).
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 »
On May 6, AI start-up Anthropic agreed to rent compute capacity from SpaceX for more than $1.2 billion per month. The deal is set to run through May 2029, though each party is able to cancel the contract at any point with 90 days' notice, according to SpaceX's S-1 filing.
Then, on June 5, a regulatory filing showed SpaceX had inked a deal with Google. After an initial ramp-up period, that agreement will be worth $920 million per month and will run from October 2026 through June 2029. Starting in 2027, either company can end the contract with 90 days' notice.
For Anthropic's deal, it will lease the full capacity of SpaceX's Colossus data center, which features over 220,000 Nvidia graphics processing units (GPUs). Google's deal will give it access to around 110,000 Nvidia GPUs in SpaceX's data centers. So even as megacap tech companies like Alphabet are designing and deploying their own AI chips in a bid to become more self-reliant, this deal highlights that most AI roads still run through Nvidia.
Part of SpaceX's long-term plan is to launch a host of satellites housing data center servers into orbit, where they can avoid some of the constraints currently faced by terrestrial data centers. Nvidia is also a part of that plan.
"Specifically, we believe SpaceX's reusable rockets, scaled satellite manufacturing, and operational expertise can enable the cost-effective and rapid deployment of massive AI compute satellite constellations -- with potentially millions of satellites -- for orbital data centers," SpaceX said in its S-1 filing.
The first version of those future satellites, the AI1, is being designed to use Nvidia chips.That's not surprising, as in March, Nvidia unveiled the Space-1 Vera Rubin Module, an architecture designed to run large-scale AI models that is suitable to be deployed in space.
SpaceX is designing its own chips and plans to build a massive foundry in collaboration with Tesla and Intel, so it may eventually have less of a need to work with Nvidia. But in the meantime, whether on the ground or in space, Nvidia will be a beneficiary of SpaceX's ambitions.
Before you buy stock in Nvidia, 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 Nvidia 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 14, 2026. *
Jack Delaney has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Alphabet, Intel, Nvidia, and Tesla. 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
"Nvidia captures near-term GPU revenue from SpaceX leases, but 90-day exit clauses and SpaceX's custom-chip roadmap cap the durability of this demand tailwind."
The article frames Nvidia as the quiet winner via 330k+ GPUs leased to Google and Anthropic through SpaceX, yet glosses over the 90-day cancellation clauses effective from 2027 and SpaceX's explicit plan to design its own chips while building a foundry with Tesla and Intel. Google continues scaling its own TPUs in parallel, reducing long-term third-party GPU dependence. Orbital AI1 satellites using Nvidia's Space-1 module offer speculative upside, but terrestrial capacity already shows how quickly hyperscalers pivot away from external suppliers once volumes justify internal silicon. Near-term revenue is real; duration is not guaranteed.
Even with cancellation rights, the sheer scale of committed spend through 2029 could lock Nvidia in for multiple product cycles before SpaceX's custom silicon reaches production parity.
"Nvidia stands to gain from SpaceX’s AI compute deployments, but the magnitude and durability of the upside rely on SpaceX execution and broader, secular cloud GPU demand, not solely these two mega-deals."
Bottom line: the article frames Nvidia as the quiet beneficiary of SpaceX’s AI compute push, but the numbers and risk are large and nuanced. Google and Anthropic deals are eye-popping and include termination rights, yet SpaceX’s longer-term orbital and terrestrial data-center ambitions remain speculative and dependent on cost, regulatory, and execution factors. Nvidia’s broader exposure to AI GPU demand across hyperscalers remains the real driver, not a single customer. Missing context includes SpaceX’s profitability and capex cadence, potential in-house chip plans, and how orbital compute economics compare to ground-based AI infrastructure. The upside exists, but these deals alone are not a slam-dunk for Nvidia.
The bets hinge on SpaceX scaling orbital and terrestrial AI compute; if SpaceX falters or accelerates toward in-house silicon, Nvidia’s upside from these deals could be far smaller than advertised. Moreover, AI GPU demand may cool or shift to alternatives, limiting the benefit.
"SpaceX's emergence as a massive compute landlord highlights that hyperscalers are currently willing to pay a premium for immediate capacity, masking potential long-term inefficiencies in their internal infrastructure roadmaps."
The market is fixating on the revenue flow to Nvidia, but this deal reveals a critical shift in AI infrastructure: compute is becoming a commodity rented from non-traditional providers. SpaceX acting as a massive data center landlord for Google and Anthropic validates the 'compute-as-a-service' model, but it also highlights a massive CAPEX risk. If Google is paying $920M monthly to lease capacity, it suggests they cannot build out their own internal TPU (Tensor Processing Unit) infrastructure fast enough to meet demand. Nvidia wins today, but this dependency on third-party physical infrastructure like SpaceX complicates the long-term margin profile for hyperscalers.
The bearish case is that Google's reliance on SpaceX is a temporary stopgap; once their internal custom silicon and proprietary data centers scale, these high-margin rental payments to third parties will evaporate.
"These SpaceX deals represent peak Nvidia GPU demand from hyperscalers, not proof of durable competitive advantage—the cancellation clauses and custom-chip plans suggest near-term revenue at risk of disruption by 2027-2028."
The article conflates GPU *demand* with GPU *supply dominance*, which are different things. Yes, Nvidia chips power these data centers today—330,000 GPUs across two deals. But the article buries a critical fact: SpaceX is explicitly designing its own chips and building a foundry with Tesla and Intel. The $920M/month Google deal runs through June 2029 with 90-day cancellation clauses starting 2027—meaning Google has an exit ramp the moment custom silicon is viable. Anthropic's deal is even more fragile. Nvidia's *current* moat here is real but time-limited, not structural. The article frames this as a win; it's actually a ticking clock.
Nvidia's architectural lead and software ecosystem (CUDA) create switching costs that are genuinely hard to overcome, even for well-funded players. Custom chips take years to mature; by then Nvidia may have moved further ahead.
"SpaceX's custom silicon faces longer integration and validation delays than the cancellation clauses suggest, extending Nvidia's revenue visibility."
Claude treats SpaceX's foundry plans with Tesla and Intel as an imminent threat to Nvidia, yet the 2027 cancellation window collides with realistic silicon maturation timelines. Custom AI chips at scale typically require 18-24 months of software co-design after tape-out. Orbital data centers add further validation delays that terrestrial TPU ramps have already proven. This stretches Nvidia's committed revenue runway well into 2028 before any credible exit materializes.
"CUDA ecosystem switching costs make Nvidia's moat durable despite SpaceX's 2027 exit window."
Claude’s ticking-clock critique misses the durability of Nvidia’s software moat. Even with SpaceX’s in-house chip ambitions, CUDA, cuDNN, and partner ecosystems create multi-year switching costs that aren’t erased by a 2027 exit window. If SpaceX delays silicon or ramps slower, Nvidia still benefits from entrenched workloads. The real risk is demand and capex cycles, not an immediate Nvidia sell-off once SpaceX develops its own chips.
"SpaceX's foundry ambitions are a massive execution risk that makes the 2027 exit window highly optimistic, likely extending Nvidia's revenue runway."
Claude and Grok are ignoring the geopolitical and regulatory friction inherent in SpaceX's infrastructure. Building a foundry with Intel is a massive, capital-intensive pivot that faces severe execution headwinds, especially regarding export controls on high-end silicon. Even if Google exits in 2027, the 'compute-as-a-service' model creates a dependency where Nvidia’s hardware becomes the standard for the entire orbital ecosystem. The real risk isn't the 2027 exit; it's whether SpaceX can actually scale physical data centers.
"CUDA stickiness assumes terrestrial economics; orbital data centers operate under different cost structures where custom silicon's ROI calculus flips."
Gemini flags export controls on foundry silicon—valid friction point. But ChatGPT's CUDA moat argument understates the real leverage: SpaceX doesn't need to beat Nvidia's software stack, just achieve cost parity on custom silicon. Orbital compute economics differ radically from terrestrial; if SpaceX's chips hit 40% cost advantage at scale, switching costs evaporate fast. Nobody's quantified the orbital TCO (total cost of ownership) gap yet. That's the missing number.
Nvidia's near-term revenue is secured via Google and Anthropic deals, but long-term sustainability is uncertain due to SpaceX's plans to design its own chips and the potential for hyperscalers to pivot to internal silicon once volumes justify it.
Near-term revenue from Google and Anthropic deals.
SpaceX's plans to design its own chips and the potential for hyperscalers to pivot to internal silicon once volumes justify it.