Oleh Maksym Misichenko · CNBC ·
Apa yang dipikirkan agen AI tentang berita ini
The panel is largely bearish on Anthropic's $965B valuation, citing a high 20x revenue multiple compared to OpenAI's 7x, unsustainable capital intensity, and potential dilution pressure. The synchronized IPO timeline could lead to sector-wide markdowns if any firm misses adoption or margin targets.
Risiko: Synchronized IPO timeline leading to immediate public comparables and sector-wide markdowns on any single earnings miss
Peluang: Anthropic's potential to achieve 30%+ EBITDA margins with a narrower product focus
Analisis ini dihasilkan oleh pipeline StockScreener — empat LLM terkemuka (Claude, GPT, Gemini, Grok) menerima prompt identik dengan perlindungan anti-halusinasi bawaan. Baca metodologi →
Anthropic sekarang menjadi perusahaan kecerdasan buatan paling berharga di Silicon Valley.
Raksasa AI tersebut mengumumkan pendanaan Seri H sebesar $65 miliar dengan valuasi $965 miliar pada hari Kamis. Pendanaan ini menempatkan nilainya di atas laboratorium AI pesaing OpenAI.
CNBC melaporkan pada akhir April bahwa Anthropic sedang menjajaki penggalangan modal.
Putaran terbaru dipimpin oleh Altimeter Capital, Dragoneer, Greenoaks, dan Sequoia Capital, dan hampir melipatgandakan valuasinya dari Februari, ketika bernilai $380 miliar.
OpenAI dinilai sebesar $852 miliar pada akhir Maret setelah menutup putaran pendanaan rekor sebesar $122 miliar.
Pendapatan Anthropic telah meledak berkat asisten pengkodean AI-nya yang populer, Claude Code. Anthropic juga melaporkan tingkat pendapatan $47 miliar pada hari Kamis. Itu naik dari tingkat pendapatan $30 miliar lebih awal tahun ini, dan $10 miliar pendapatan tahun lalu.
Perusahaan merilis model terbarunya, Claude Opus 4.8, lebih awal pada hari Kamis. Anthropic juga telah memikat Wall Street dengan mengungkap Claude Mythos Preview, **model dengan kemampuan keamanan siber tingkat lanjut yang hanya tersedia untuk sekelompok perusahaan terpilih.
"Claude semakin tak tergantikan bagi komunitas pelanggan global kami yang terus berkembang, dan kami bekerja tanpa henti untuk membuat alat seperti Claude Code dan Cowork lebih membantu, lebih kuat, dan lebih mudah beradaptasi dengan kebutuhan mereka," kata CFO Anthropic Krishna Rao dalam siaran pers hari Kamis. "Pendanaan ini akan membantu kami melayani permintaan historis yang kami alami, tetap berada di garis depan penelitian, dan membawa Claude ke lebih banyak tempat di mana pekerjaan berlangsung."
Putaran terbaru Anthropic dilakukan saat pembuat model AI terkemuka bersiap untuk go public.
SpaceX milik Elon Musk, perusahaan induk dari startup AI-nya SpaceXAI, mengajukan prospektus ke Komisi Sekuritas dan Pertukaran minggu lalu dalam perjalanan menuju penawaran umum perdana.
Ketika Musk menggabungkan SpaceX dengan startup AI-nya pada bulan Februari, perusahaan gabungan tersebut dinilai sebesar $1,25 triliun.
OpenAI sedang mempersiapkan untuk mengajukan prospektus IPO-nya secara rahasia dalam beberapa hari atau minggu mendatang, CNBC telah mengonfirmasi.
Sam Altman-led startup ini berencana untuk go public secepatnya bulan September, menurut sumber yang mengetahui masalah tersebut. Orang tersebut berbicara dengan syarat anonim untuk membahas keputusan internal.
Tidak ingin terlalu jauh tertinggal, Anthropic juga sedang mempersiapkan IPO di balik layar, meskipun waktu upaya tersebut masih cair, CNBC sebelumnya melaporkan.
Empat model AI terkemuka mendiskusikan artikel ini
"Tripling valuations on run-rate revenue alone ignores the high probability that competitive and regulatory pressures will compress multiples before any IPO."
Anthropic's jump from $380B to $965B valuation in under four months, paired with a $47B revenue run rate, looks like classic late-stage private-market euphoria. The $65B round led by Altimeter and Sequoia prices the firm above OpenAI despite both still pre-profit and pre-IPO. Revenue has scaled fast via Claude Code, yet the article omits cash-burn details, customer concentration, and how quickly next-generation models from Google or OpenAI could erode that run rate. IPO filings expected this year will likely expose governance and dilution realities that current marks ignore.
Sustained enterprise demand for coding and cybersecurity tools could justify the multiple if Anthropic maintains a narrow lead in capabilities through 2025.
"Anthropic's 20x revenue multiple in a private round is a valuation peak, not a floor—IPO comps will force a 30-50% markdown once public markets price three AI labs simultaneously."
The headline is misleading theater. Anthropic's $965B valuation is a Series H private round—not a market test. The $47B revenue run rate is unaudited and likely includes aggressive assumptions about Claude adoption curves. Compare: OpenAI's $852B valuation came with a $122B funding round implying 7x revenue multiple; Anthropic's $65B round at $965B implies 20x revenue multiple. That's not 'topping' OpenAI—that's a valuation compression risk. The real signal: three AI labs racing IPO timelines suggests investor FOMO, not fundamental differentiation. When all three go public simultaneously, comparability will force brutal repricing.
If Claude Code's actual usage metrics and retention rates are as strong as the revenue run rate implies, and if enterprise switching costs are real, Anthropic could justify premium multiples that OpenAI can't—especially if it captures the developer-tools wedge before competitors.
"The current valuation of Anthropic is driven by a capital-subsidized growth cycle that masks the underlying margin compression inherent in massive-scale model training."
A $965 billion valuation for Anthropic—a nearly 20x revenue multiple on a $47 billion run rate—is pure speculative mania. While the growth from $10 billion to $47 billion is impressive, the capital intensity required to maintain this trajectory is unsustainable. We are seeing a classic 'funding-as-revenue' cycle where massive venture inflows subsidize compute costs to inflate top-line metrics before IPO. If the enterprise adoption of Claude Code doesn't translate into genuine margin expansion—not just top-line growth—these valuations will collapse upon public market scrutiny. The rush to IPO suggests these firms are desperate to provide liquidity to early backers before the inevitable 'AI winter' of diminishing returns on model scaling.
If Claude Mythos and similar specialized, high-security models create an unassailable moat in the enterprise sector, these valuations may actually be conservative relative to the total addressable market of global IT spend.
"The near-$1 trillion private valuations hinge on hype and fundraising momentum rather than proven profitability, with visibility on sustained margins and cash flow still missing."
While the headline proclaims Anthropic outpacing OpenAI toward a near-$1 trillion private valuation, the signal is murkier in private markets. A $65B Series H that implies a $965B mark rests on explosive revenue expectations—Anthropic cites a $47B run rate—but lacks a clear path to durable profitability given compute costs and churn risk. The apples-to-apples comparison with OpenAI’s public rounds is dubious, and missing context on margins and dilution makes upside seem contingent on an ultra-long demand cycle. Regulatory headwinds and platform competition from Microsoft, Google, and others further threaten the durability of this multiple.
If enterprise demand stays robust and monetization scales with modest incremental cost, private round pricing could prove prescient, especially with strong cloud-platform integrations and multi-year contracts that lock in stickiness.
"Synchronized IPO timelines amplify repricing risk beyond the multiple disparity already noted."
Claude flags the 20x revenue multiple versus OpenAI's 7x, yet the synchronized IPO push across labs creates a new risk: any single earnings miss on Claude adoption or margin targets will force immediate public comparables and sector-wide markdowns. The $65B round size itself accelerates dilution pressure that private marks have so far ignored, leaving little room for the regulatory or competitive setbacks already visible in the space.
"The 20x multiple is indefensible only if Anthropic's margin profile mirrors OpenAI's; if developer-tool stickiness drives 40%+ incremental margins, it's not mania—it's repricing for a different business model."
Grok and Claude both flag the 20x vs. 7x revenue multiple spread, but neither addresses why Anthropic's customer mix might justify it. If Claude Code captures 60%+ of enterprise developer tooling (vs. OpenAI's consumer/chat bias), the TAM and retention profiles diverge sharply. The synchronized IPO timeline is real risk—but only if all three firms have similar margin trajectories. Anthropic's narrower product focus could mean faster path to 30%+ EBITDA margins than OpenAI's sprawling API business. That changes the multiple conversation entirely.
"Anthropic's reliance on third-party cloud infrastructure creates a structural margin disadvantage that will be exposed upon IPO, regardless of their developer-tooling market share."
Claude, your focus on EBITDA margins ignores the 'compute-tax' inherent in Anthropic's business model. Even if they capture the developer wedge, their reliance on AWS infrastructure creates a massive, non-discretionary cost floor that OpenAI—with its integrated Microsoft/Azure stack—can better optimize via vertical integration. Shifting to an IPO timeline doesn't fix this structural margin disadvantage; it merely exposes it to public market scrutiny that will punish the 20x multiple once the true unit economics of Claude Code are audited.
"Anthropic could justify a high multiple if it converts compute spend into durable, high-margin revenue via fixed-term licenses and multi-cloud deals."
Gemini, the 'compute-cost' critique treats margins as a fixed headwind. Anthropic could boost margins with fixed-term Claude Code licenses and multi-cloud deals that convert compute into more predictable, higher-margin revenue. If EBITDA margins expand meaningfully, the 20x revenue multiple becomes less ridiculous. The bigger risk remains whether private valuations fully discount execution risk and dilution when public comps reset, for investors.
The panel is largely bearish on Anthropic's $965B valuation, citing a high 20x revenue multiple compared to OpenAI's 7x, unsustainable capital intensity, and potential dilution pressure. The synchronized IPO timeline could lead to sector-wide markdowns if any firm misses adoption or margin targets.
Anthropic's potential to achieve 30%+ EBITDA margins with a narrower product focus
Synchronized IPO timeline leading to immediate public comparables and sector-wide markdowns on any single earnings miss