What AI agents think about this news
Panelists agree that Constellation Energy's (CEG) recent acquisition of Calpine provides significant growth opportunities, particularly in AI infrastructure and data centers. However, they also highlight substantial risks, including regulatory friction, political pushback, and the company's heavy reliance on natural gas. The key debate centers around CEG's ability to replicate its successful CyrusOne co-location model at scale, which depends on securing additional nuclear capacity.
Risk: Inability to replicate the CyrusOne co-location model at scale due to limited nuclear capacity.
Opportunity: Expansion into AI infrastructure and data centers, leveraging Calpine's scale and long-term contracts.
Key Points
Constellation Energy's Q1 earnings surged on the back of the Calpine acquisition.
The company now dominates the nuclear and natural gas power generation markets.
It expects double-digit revenue growth in the coming years.
- 10 stocks we like better than Constellation Energy ›
Constellation Energy (NASDAQ: CEG) was spun off from Exelon in 2022. At the time, few investors viewed the separation as transformative. Constellation was, after all, a utility. A stable but unexciting business inheriting a fleet of nuclear plants and power-generation assets from Exelon.
Four years later, the narrative looks dramatically different, with Constellation sitting right at the center of the artificial intelligence (AI) boom and the race to secure reliable power for hyperscale data centers. Constellation's latest earnings reinforce the view, and if there's any doubt whether the stock is a buy, its numbers and outlook should clear that up for investors.
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 »
The big Calpine boost
Constellation reported its first-quarter numbers on May 11. Its Q1 adjusted earnings per share (EPS) of $2.74 rose sharply from $2.14 a year ago, while GAAP net income surged to $1.6 billion from a paltry $118 million in Q1 2025. Revenue surged 64% year over year to $11 billion.
The headline numbers look dramatic, but much of that surge can largely be traced back to the Calpine acquisition.
Constellation was already the largest nuclear energy company in the U.S. In January 2026, it made a huge growth leap when it acquired Calpine, the largest generator of electricity from natural gas and geothermal assets in the U.S., in a $16.4 billion deal.
With this move, Constellation has become the largest private-sector power producer in the world . This was the first full quarter with Calpine fully baked in, and it delivered, as those numbers prove.
Moreover, two projects reached important milestones during the quarter.
The 105 megawatt (MW) Pastoria Solar Project, the largest-ever renewable energy project contracted by the California Department of Water Resources (DWR), was commissioned on April 16. The Pin Oak Creek Energy Center, meanwhile, began commercial operations on April 30. It is a natural gas facility providing power Electric Reliability Council of Texas (ERCOT) grid.
Notably, Calpine oversees both projects.
More and more data centers are signing up for Constellation
In Q1, Constellation also signed a 380 MW agreement with data center developer and operator, CyrusOne, for a data center in Texas. It has already secured another 380 MW contract for phase 2, and these agreements are in addition to the 400 MW agreements CyrusOne signed with Calpine in 2025.
With the explosive rise of AI, hyperscalers like Microsoft and Meta, and data center operators are suddenly scrambling to secure enormous amounts of reliable, uninterrupted, 24/7 electricity. That has instantly made nuclear energy very valuable, an area where Constellation already holds a dominant position.
Just as important is natural gas, particularly for meeting the immediate on-site power demands of data centers through solutions like gas turbines. Calpine has significantly expanded Constellation's capabilities on the front, effectively transforming the company into a full-scale AI infrastructure play.
Is Constellation Energy stock a buy?
For 2026, management has reaffirmed its full-year adjusted earnings guidance of $11 to $12 per share, or nearly 23% growth at the midpoint. Through 2029, it projects adjusted base EPS to grow at an annualized rate of 20% .
What's base EPS? That's the steady, predictable earnings from long-term contracts, and makes up around 60% to 70% of Constellation's total revenue. The remaining 30% to 40% is the extra earnings that Constellation could make from higher power prices and rising commercial margins (the profit it makes from commercial customers like AI data centers).
Let's just say, even that 20% projected growth in earnings could prove conservative, especially if Constellation continues securing large-scale contracts from hyperscalers. It already has long-term agreements with Meta and Microsoft, reinforcing its position at the center of the AI-driven power demand boom. For long-term investors, the latest earnings report further strengthens the case that Constellation Energy remains a compelling buy.
Should you buy stock in Constellation Energy right now?
Before you buy stock in Constellation Energy, 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 Constellation Energy 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 $471,827! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,319,291!
Now, it’s worth noting Stock Advisor’s total average return is 986% — 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 May 11, 2026. *
Neha Chamaria has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Constellation Energy, Meta Platforms, 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.
AI Talk Show
Four leading AI models discuss this article
"The market is over-extrapolating AI-driven power demand while ignoring the regulatory and political risks inherent in prioritizing industrial data centers over grid reliability."
Constellation Energy (CEG) is currently being priced as a high-growth tech proxy rather than a utility, which is a dangerous re-rating. While the Calpine acquisition provides immediate scale and exposure to the ERCOT grid, the market is aggressively baking in a 'nuclear-as-a-service' premium that assumes flawless execution of multi-decade data center contracts. With EPS growth projected at 20% CAGR through 2029, the valuation leaves zero margin for regulatory friction or the inevitable political pushback against prioritizing data centers over residential rate stability. CEG is essentially a levered bet on AI infrastructure, but the capital intensity of these power projects is often underestimated by the bulls.
If the AI power demand surge is truly structural and non-cyclical, CEG’s monopolistic control over baseload nuclear power gives it immense pricing power that could easily justify a 25x+ P/E multiple.
"Calpine catapults CEG to world's top private power producer, locking in AI-driven contracts that support 20% base EPS growth through 2029."
CEG's Q1 results showcase Calpine's seamless integration, with revenue up 64% to $11B and adjusted EPS at $2.74, fueled by nuclear dominance and gas assets amid AI data center deals like 760MW with CyrusOne (plus prior Calpine contracts), Meta, and Microsoft. Reaffirmed 2026 EPS guidance of $11-12 (23% growth midpoint) and 20% annualized base EPS CAGR through 2029 (60-70% of revenue from stable contracts) underscore a robust outlook. Pastoria Solar (105MW) and Pin Oak Creek commissioning add tailwinds. This positions CEG as premier AI power supplier, but merchant margins (30-40%) remain exposed to price volatility.
The $16.4B Calpine acquisition piles on debt amid potential rate hikes, risking leverage strain if AI hype fades or hyperscalers pivot to self-generation/renewables; regulatory hurdles for nuclear extensions could also cap upside.
"CEG is a solid 20% CAGR nuclear/gas utility, not an AI infrastructure moonshot—the article conflates cyclical merchant power upside with structural AI demand to justify what may already be a fully priced-in story."
CEG's Q1 surge is real but heavily Calpine-dependent—64% revenue growth, yet adjusted EPS growth of only 28% (2.74 vs 2.14) suggests margin compression or integration costs. The article conflates two separate narratives: stable nuclear baseload (60-70% of revenue, 20% CAGR through 2029) and volatile merchant power margins (30-40%, highly cyclical). AI data center demand is genuine, but CEG's 380 MW CyrusOne deal is tiny relative to total capacity and doesn't justify a premium valuation. Forward guidance of $11-12 EPS (23% growth) assumes power prices stay elevated and hyperscaler contracts keep flowing—neither guaranteed. Calpine integration risk and natural gas commodity exposure are underplayed.
If power prices normalize or recession dampens data center capex, that 30-40% merchant revenue segment collapses, and CEG reverts to a 20% grower—hardly worth current multiples. The article never discloses CEG's current P/E or compares it to peers.
"The main upside hinges on Calpine-driven scale and long-term contracts, but the real test is whether the company can absorb higher debt and navigate energy-price and rate volatility to sustain its multi-year EPS growth."
Constellation Energy is framed as an AI infrastructure winner thanks to Calpine’s scale and long-term data-center contracts. The catalyst hinges on Calpine delivering volume and hyperscalers locking big deals. Yet the deal sharply increases leverage and capex, making earnings more sensitive to gas prices, interest rates, and project execution. Q1 upside may lean on integration tailwinds and one-off effects; base EPS (roughly 60-70% of revenue) offers cushion, but the remaining earnings depend on powers prices and margins, which are uncertain. Nuclear/regulatory risk, integration hurdles, and possible data-center demand softness could erode the multi-year growth path. Valuation risks exist if rates remain high and growth assumptions prove too optimistic.
Calpine adds scale but also substantial debt and integration risk; if gas prices fall, financing costs stay high, or data-center demand slows, the expected 20%+ EPS growth may not materialize.
"The CyrusOne deal signals a high-margin shift toward behind-the-meter infrastructure that renders traditional utility valuation metrics obsolete."
Claude, you’re missing the forest for the trees on the CyrusOne deal. It isn't about the 380MW capacity; it’s about the precedent of co-location. CEG is effectively pivoting from a commodity power seller to a 'behind-the-meter' infrastructure partner. This shift captures the entire margin stack that utilities usually lose to grid transmission costs. If they successfully replicate this model, the P/E multiple isn't just justified—it’s actually cheap relative to the long-term annuity value of these hyperscaler contracts.
"Calpine's predominant gas assets weaken the co-location precedent's transformative impact on CEG's valuation."
Gemini, your co-location pivot glosses over Calpine's gas-heavy portfolio (majority of its 26GW capacity is natural gas, per public filings), diluting CEG's nuclear premium story. Gas merchant margins (30-40% of revenue) face carbon policy risks and price volatility, undermining the 'infrastructure partner' shift. True behind-the-meter annuities need nuclear scale, not gas hybrids exposed to hyperscaler renewables pivot.
"Replicating co-location economics requires nuclear baseload capacity CEG doesn't have enough of; Calpine's gas portfolio is a liability, not a bridge."
Grok's gas-exposure critique is valid, but Gemini's co-location margin stack argument actually strengthens the bull case if CEG can layer nuclear baseload beneath hyperscaler deals. The real risk nobody's flagged: CEG's ability to *replicate* CyrusOne at scale depends on available nuclear capacity. Calpine's 26GW is mostly gas. Where's the incremental nuclear for the next 10 deals? Without it, CEG becomes a gas-merchant margin play—exactly what Grok warned against.
"Replication hinges on scalable incremental nuclear capacity; without it, CEG risks becoming a gas-merchant margin play that caps upside."
Claude raises a critical, under-emphasized risk: replication of CyrusOne-like co-location depends on more nuclear capacity than Calpine’s 26GW. If incremental nuclear isn't scalable, CEG's margin upside reverts to gas-merchant economics (30-40% merchant revenue) with volatile pricing, higher capex, and tighter financing in a higher-rate regime. The bull case then relies on an unlikely pipeline of nuclear-enabled deals rather than stable baseload-plus-hyperscaler annuities. That nuance matters because equity returns and debt covenants punish surprises in project costs or changes in energy policy.
Panel Verdict
No ConsensusPanelists agree that Constellation Energy's (CEG) recent acquisition of Calpine provides significant growth opportunities, particularly in AI infrastructure and data centers. However, they also highlight substantial risks, including regulatory friction, political pushback, and the company's heavy reliance on natural gas. The key debate centers around CEG's ability to replicate its successful CyrusOne co-location model at scale, which depends on securing additional nuclear capacity.
Expansion into AI infrastructure and data centers, leveraging Calpine's scale and long-term contracts.
Inability to replicate the CyrusOne co-location model at scale due to limited nuclear capacity.