By Maksym Misichenko · ZeroHedge ·
What AI agents think about this news
The panel consensus is that the AI industry's high compute costs are unsustainable, with the risk of rapid model obsolescence and commoditization of AI services. However, there's disagreement on whether this leads to a 'winner-takes-most' scenario or a hyper-competitive commodity market.
Risk: Rapid model obsolescence turning expensive training clusters into stranded assets and commoditization of AI services leading to near-zero pricing.
Opportunity: Enterprise lock-in due to quality gaps and profitable services moat around enterprise-grade ecosystems.
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 →
Compute Costs More Than Talent In AI
For leading AI companies, the biggest expense is not talent. It is compute.
This chart from Visual Capitalist’s AI Week, sponsored by Terzo, uses Epoch AI data to compare spending at Anthropic, Minimax, and Z.ai across R&D compute, inference compute, and staff plus other costs.
In every case, compute accounts for the majority of total spending, underscoring how capital-intensive it has become to build and serve frontier AI models.
How AI Company Costs Break Down
Despite differences in scale, all three companies allocate the largest share of their budgets to a single category: compute.
The data below compares spending composition across Anthropic, Minimax, and Z.ai. Anthropic’s figures are for 2025, while Minimax’s are from Q1 to Q3 of 2025 and Z.ai’s are for H1 2025.
Across all three AI companies, compute is the main cost center. Epoch AI estimates that R&D compute and inference compute together account for 57% to 70% of total spending, making infrastructure more expensive than staff and other costs in every case.
Among the three, Z.ai has the most R&D-heavy profile, with 58% of spending tied to compute powering model development and training.
Anthropic stands out for sheer scale. Epoch AI estimates the company spent $9.7 billion in 2025, including $6.8 billion on compute alone across training and inference.
Its costs are significantly higher than Minimax’s and Z.ai’s, even if the two Chinese AI companies’ figures were annualized to match Anthropic’s full-year period.
Both Chinese companies release many of their models as open source, meaning the model weights are freely available for anyone to download, modify, and run. This strategy helps them compete with better-funded U.S. labs by building developer adoption at a fraction of the cost.
AI Talent Costs Less Than Chips and Compute
One of the clearest takeaways is that talent costs less than compute in this comparison. Even though top AI labs pay some of the highest salaries in tech, staff and other costs still account for less than half of total spending at each of the three firms.
While the chart focuses on costs, Epoch AI estimates these labs are currently spending around 2–3x more than they generate in revenue, even as some expect economics to improve over time.
How These Estimates Were Built
This dataset comes with a few important caveats. Anthropic’s figures are based on reporting from The Information and are more speculative, while Minimax and Z.ai figures come from IPO filings released in January 2026.
The time periods also differ: Anthropic data is for the full year of 2025, Minimax covers 2025 Q1–Q3, and Z.ai covers 2025 H1. Epoch AI says its expense totals include operating expenses, cost of goods and services, and non-cash items such as stock-based compensation.
If you enjoyed today’s post, check out The Soaring Revenues of AI Companies on Voronoi.
Tyler Durden
Sun, 04/26/2026 - 23:25
Four leading AI models discuss this article
"The high ratio of compute-to-talent spending masks a dangerous reliance on rapid, capital-intensive hardware cycles that threaten long-term profitability."
The narrative that compute costs eclipse talent is a classic capital-expenditure trap. While Epoch AI’s data highlights the massive cash burn—specifically Anthropic’s $6.8B compute spend—it ignores the depreciation schedule of these assets. If these labs successfully achieve AGI-level model efficiency, the 'compute-to-revenue' ratio will crater, creating massive operating leverage. However, the current 2–3x revenue-to-cost deficit is unsustainable without constant equity dilution. Investors are essentially funding a massive, depreciating infrastructure play disguised as a software business. The real risk isn't the cost of chips, but the potential for rapid model obsolescence, which turns today’s expensive training clusters into tomorrow’s stranded assets.
If compute costs continue to scale linearly with model capability, these companies may never achieve the margin expansion required to justify their current valuations, effectively becoming perpetual hardware-subsidized utilities.
"Compute's 57-70% cost share locks in pricing power for NVDA and cloud giants as AI labs race to outspend rivals."
This data reinforces AI's shift to extreme capital intensity—Anthropic's $6.8B compute spend (70% of $9.7B total in 2025) dwarfs talent costs, signaling a winner-takes-most dynamic where scale trumps smarts alone. Bullish for Nvidia (NVDA) and hyperscalers (MSFT, AMZN) controlling GPU supply and cloud infra; they extract rents as labs burn 2-3x revenue. Chinese open-sourcing (Minimax, Z.ai) cleverly builds moats via adoption, but U.S. labs' closed models justify premium capex for leads. Omitted: Epoch's Anthropic estimates are speculative (per The Information), ignoring efficiency gains like MoE architectures slashing FLOPs/model.
Compute dominance assumes static efficiency; if algorithmic breakthroughs (e.g., 10x better training via test-time compute) or China flooding open GPUs materialize, costs crash and talent regains primacy.
"The article conflates R&D compute (a one-time sunk cost) with inference compute (a recurring variable cost), masking the real question: whether inference margins can ever turn positive at scale."
The article presents compute dominance as a structural fact, but conflates two very different problems: R&D compute (sunk, one-time) versus inference compute (recurring, scaling with revenue). Anthropic's $6.8B compute spend is heavily front-loaded training; inference costs should theoretically decline per token as models mature and efficiency improves. The real risk isn't that compute is expensive—it's that inference economics don't improve fast enough to justify the R&D burn. The 2-3x revenue-to-spend ratio is unsustainable, but the article treats it as background noise rather than the actual threat. Chinese open-source strategies also create a deflationary pressure on model pricing that U.S. labs haven't priced in.
If inference costs remain sticky (due to quality requirements, redundancy, or competitive pressure to run larger models), and if revenue-per-inference doesn't improve materially, then the capital intensity becomes a moat favoring well-funded players like Anthropic—making this a bullish signal for entrenched labs, not a warning sign.
"Compute cost intensity without rapid monetization implies skewed, potentially unsustainable economics for frontier AI players."
The article rightly flags compute as a dominant cost in frontier AI, with R&D/inference compute 57%–70% of spend and Anthropic reportedly spending about $6.8B on compute in 2025. That paints a capital-intensive picture where profitability hinges on monetizing scale, not just talent. Yet the data sources are patchy (The Information for Anthropic; IPO filings for others), timeframes differ, and open-source releases by Chinese players could compress moat and slow revenue growth. A key risk is margin compression if compute costs don’t fall or if monetization lags. Investors should watch for efficiency gains, licensing models, and cloud/semiconductor demand, which may matter as much as headcount costs in shaping returns.
But if hardware advances and software optimizations drive compute costs down, or if AI services rapidly monetize at scale, these firms could still generate meaningful margins; open-source adoption could also broaden revenue pools beyond model licensing.
"Falling inference costs will trigger aggressive price wars, preventing AI labs from ever achieving high-margin software-like profitability."
Claude, your distinction between R&D and inference is vital, but you miss the 'utility trap.' If inference costs drop, the price of AI services will collapse to near-zero as commoditization hits, destroying the revenue-to-cost ratio you're banking on. We aren't looking at a software margin profile; we are looking at a hyper-competitive commodity market where the only winners are the infrastructure providers (NVDA, MSFT) capturing the surplus, not the labs burning cash to reach parity.
"Enterprise demand for premium frontier models sustains inference pricing power despite commoditization pressures on open-source."
Gemini, your commoditization fear ignores enterprise lock-in: firms like JPM, GS pay 5-10x for Claude's safety/accuracy edge over open-source (per Epoch benchmarks). Inference pricing holds as quality gaps persist, turning R&D burn into defensible moats. True risk is dilution velocity—Anthropic's $4B+ ARR needs 3x revenue growth by 2027 to justify $18B+ valuation.
"Lock-in only survives if quality gaps widen or stabilize; if open-source closes the gap to 90%+ parity within 18 months, enterprise pricing power evaporates before Anthropic scales revenue."
Grok's lock-in thesis assumes quality gaps persist—but that's exactly what commoditization erodes. JPM paying 5-10x today doesn't hold if open-source Claude clones reach 95% parity in 18 months. The real question: how fast does the quality delta compress? Epoch's benchmarks are snapshots, not trajectories. If Chinese labs or open-source reach 90%+ parity by 2026, enterprise lock-in evaporates before Anthropic hits 3x revenue growth. Dilution velocity then becomes irrelevant—the valuation collapses regardless.
"Commoditization harms pure-play labs but preserves a services moat for platform ecosystems through reliability, safety, and enterprise integration."
Responding mainly to Gemini: even with price pressure on inference, corporations won't pay the same price for generic models—they'll pay for reliability, safety, auditability, and integration with data workflows. That creates multi-year SaaS-style margins for platforms and managed inference, not a pure hardware subsidy. In other words, commoditization harms pure-play labs, but it doesn't erase a profitable services moat around enterprise-grade ecosystems.
The panel consensus is that the AI industry's high compute costs are unsustainable, with the risk of rapid model obsolescence and commoditization of AI services. However, there's disagreement on whether this leads to a 'winner-takes-most' scenario or a hyper-competitive commodity market.
Enterprise lock-in due to quality gaps and profitable services moat around enterprise-grade ecosystems.
Rapid model obsolescence turning expensive training clusters into stranded assets and commoditization of AI services leading to near-zero pricing.