llms.blog
AI

Anthropic Revenue Run Rate Tops $65 Billion Ahead of Planned Public Listing

Anthropic's annualized revenue run rate reached approximately $65 billion at the end of July 2026, according to reporting by Bloomberg on August 17, with corroborating details reported by Reuters and Axios. The figure marks an $18 billion expansion over two months from the $47 billion run rate reported during Anthropic's Series H financing in late May, and up from $9 billion at the close of 2025. The acceleration highlights deepening enterprise adoption of Claude across corporate workflows, wit

axc
axc
2 min
Anthropic Revenue Run Rate Tops $65 Billion Ahead of Planned Public Listing

Anthropic's annualized revenue run rate reached approximately $65 billion at the end of July 2026, according to reporting by Bloomberg on August 17, with corroborating details reported by Reuters and Axios. The figure marks an $18 billion expansion over two months from the $47 billion run rate reported during Anthropic's Series H financing in late May, and up from $9 billion at the close of 2025.

The acceleration highlights deepening enterprise adoption of Claude across corporate workflows, with products such as Claude Code and Cowork serving as primary drivers. According to the Financial Times, some investors participating in recent funding rounds project Anthropic's annualized revenue run rate could reach between $100 billion and $120 billion by the end of 2026. Anthropic has not published formal revenue guidance to confirm that range.

Anthropic infrastructure and revenue scaling

Capital Structure and Infrastructure Commitments

Anthropic established its previous public valuation benchmark on May 28, 2026, closing a $65 billion Series H funding round at a $965 billion post-money valuation. That round was led by Altimeter Capital, Dragoneer, Greenoaks, and Sequoia Capital, with co-leads including Capital Group, Coatue, D1 Capital Partners, GIC, ICONIQ, and XN. The financing also incorporated $15 billion in previously committed hyperscaler investments, including $5 billion from Amazon, alongside strategic hardware participation from Micron, Samsung, and SK hynix.

To service customer demand and support frontier model training, Anthropic has assembled extensive computing and energy agreements:

  • Up to 5 gigawatts of power and data center capacity with Amazon.
  • 5 gigawatts of next-generation custom TPU capacity developed with Google and Broadcom.
  • Additional GPU cluster access contracted through SpaceX infrastructure.

The Path to Public Markets

Both Anthropic and OpenAI have submitted confidential draft registration paperwork for initial public offerings with US regulators. Anthropic is positioning for an IPO as early as autumn 2026, targeting a public valuation of $2 trillion or more, according to the Financial Times.

Competitor comparisons reflect contrasting growth rates. OpenAI's annualized revenue run rate recently reached $40 billion, according to an internal message from co-founder Greg Brockman reported by Axios. However, direct financial comparisons between private frontier labs remain difficult because companies calculate annualized run rates using differing internal formulas and time horizons.

Revenue run rates extrapolate short-term billing over an entire year and do not represent audited GAAP revenue. Audited financial metrics, gross margins, and actual capital expenditure allocations will only become verifiable when Anthropic releases its public S-1 registration statement prior to pricing its listing.

Sources

AIAnthropicClaudeBusinessEnterprise
ShareX (Twitter)LinkedIn

Written by

axc

More to read

  • Distributed RLHF Frameworks in Production: Comparing OpenRLHF, verl, and TRL Architecture, Ray Resource Scheduling, and Rollout-Training Co-Location

    Post-training alignment has shifted from offline preference tuning to large-scale, online reinforcement learning. Modern post-training loops for reasoning models, agentic workflows, and conversational alignment require coordinating multiple distinct neural network roles simultaneously. Under standard Proximal Policy Optimization (PPO), an RL infrastructure pipeline must manage up to four distinct model instances: the Actor (the active policy undergoing gradient updates), the Critic (the value mo

    1 min

  • Forward KL vs. Reverse KL Divergence: Mode Covering, Mode Seeking, and the Alignment Dynamics of Large Language Models

    Forward KL vs. Reverse KL Divergence: Mode Covering, Mode Seeking, and the Alignment Dynamics of Large Language Models Every phase of modern large language model development, from multi-trillion token pre-training to reinforcement learning from human feedback (RLHF) and student model distillation, fundamentally revolves around minimizing statistical distance between probability distributions. The primary mathematical tool utilized for this purpose is the Kullback-Leibler (KL) divergence, introd

    1 min

  • Embedding Model Fine-Tuning in Production: Hard Negative Mining, Synthetic Data Pipelines, and Contrastive Distillation

    Production retrieval-augmented generation (RAG) and semantic search architectures frequently suffer from domain mismatch when relying on general-purpose embedding models. Off-the-shelf bi-encoders trained on broad web corpora often experience a 15% to 30% degradation in retrieval metrics such as NDCG@10 and MRR@10 when deployed on specialized enterprise corpora, including proprietary codebases, internal API schemas, clinical trials, and technical documentation. While downstream cross-encoder re

    1 min