Anthropic Signs $10B Compute Deal With Cloud Startup That Didn't Exist Six Months Ago

Anthropic has locked in $10 billion worth of computing capacity from Volta Infra Holdings, a cloud infrastructure startup founded in early 2026, in a six-year deal that underscores the AI industry's increasingly aggressive scramble for compute. The deal, reported by Bloomberg, will draw on a data center in Tydal, Norway, where Bitcoin miner Bitdeer Technologies operates hydropower-fed infrastructure packed with Nvidia's latest Vera Rubin chips. Volta describes the capacity at 133 megawatt

1 min
Anthropic Signs $10B Compute Deal With Cloud Startup That Didn't Exist Six Months Ago

Anthropic has locked in $10 billion worth of computing capacity from Volta Infra Holdings, a cloud infrastructure startup founded in early 2026, in a six-year deal that underscores the AI industry's increasingly aggressive scramble for compute.

The deal, reported by Bloomberg, will draw on a data center in Tydal, Norway, where Bitcoin miner Bitdeer Technologies operates hydropower-fed infrastructure packed with Nvidia's latest Vera Rubin chips. Volta describes the capacity at 133 megawatts, with delivery in two phases through March 2027. Bitdeer's stock rose 14 percent after the announcement.

Volta was founded by former managers from asset manager Brookfield. Alongside the Anthropic deal, the company has raised $300 million in venture capital led by Andreessen Horowitz and Altimeter Capital, with Nvidia and Michael Dell also participating. That round valued the company at $2.4 billion. Volta has separately established a $5 billion financing pool to help customers cover the upfront cost of AI chips.

The deal adds to Anthropic's growing portfolio of compute agreements. The company already has capacity arrangements with Google and Broadcom, a multi-year commitment to spend on Amazon Web Services as part of Amazon's $33 billion investment, and deals with SpaceX for GPU access and AMD for chip supply.

The Volta arrangement highlights the circular dependencies forming in the AI infrastructure market. Nvidia is both an investor in Volta and the supplier of the chips the startup deploys, a pattern that has drawn attention from critics who warn that overlapping financial relationships between chip makers and AI developers could amplify losses if AI demand falls short of expectations.

The Norwegian data center also reflects a broader industry shift toward locating compute capacity in regions with abundant renewable energy, following recent EPA guidance that exempts islanded data center power plants from Clean Air Act requirements.

Sources

Written by

More to read

  • Continuous Batching and Request Scheduling in Production LLM Serving: Comparing Orca, FastServe, Sarathi-Serve, and vLLM Architecture, Preemption Policies, Chunked Prefill Interleaving, and TTFT-TBT Trade-Offs

    Autoregressive large language model serving exhibits a fundamental architectural tension between compute utilization and latency guarantees. Standard deep learning inference pipelines rely on static request-level batching, where incoming queries are grouped into a fixed tensor, executed across forward passes until all sequences finish, and evicted simultaneously. In transformer-based text generation, static batching collapses serving efficiency. Because sequence lengths vary widely and token gen

    1 min
  • Figure AI Unveils Index Platform with 16 Million Crowdsourced Videos for Robot Foundation Models

    Humanoid robotics startup Figure AI has launched Index, a global crowdsourced data collection platform engineered to capture real-world human task demonstrations at scale. Operating in stealth for four months prior to its public unveiling, the platform has compiled 16 million video demonstrations from contributors across 108 countries, generating embodied training data for Figure's physical AI foundation models. The initiative directly targets the primary bottleneck in scaling embodied AI: the

    1 min
  • Anthropic Claude Autonomously Designs Validated Protein Binders Across 14 Targets

    Anthropic has released experimental results demonstrating autonomous de novo protein binder design using its frontier Claude models, backed by physical wet-lab validation from two independent contract research organizations. In empirical testing against 15 target proteins, Claude-designed mini-binders successfully bound to 14 targets, delivering an overall hit rate of 26.8% and a 49% binding rate for its top-ranked candidates. The campaign evaluated Claude Opus 4.8 and a preview build of Claude

    1 min