Anthropic doubles Claude Code rate limits, secures 220,000 Nvidia GPUs via SpaceX Colossus 1 deal
Anthropic doubled Claude Code's five-hour rate limits across Pro, Max, Team, and Enterprise plans effective Tuesday, removing peak-hours throttling for Pro and Max users. The capacity expansion comes from an exclusive agreement securing all compute at SpaceX's Colossus 1 data center, which provides over 300 megawatts and more than 220,000 Nvidia GPUs.
Anthropic doubles Claude Code rate limits, secures 220,000 Nvidia GPUs via SpaceX Colossus 1 deal
Anthropic doubled Claude Code's five-hour rate limits across Pro, Max, Team, and Enterprise plans effective Tuesday, while also raising Claude Opus API rate limits considerably. The capacity expansion is backed by a new agreement giving Anthropic exclusive access to SpaceX's Colossus 1 data center.
Rate limit changes
The changes took effect immediately:
- Claude Code's five-hour rate limits doubled across Pro ($20/month), Max ($100/month), Team, and seat-based Enterprise plans
- Peak-hours throttling removed for Claude Code on Pro and Max accounts
- Claude Opus API rate limits raised, with new ceilings published in Anthropic's documentation
Anthropic confirmed the increases apply to Claude Code usage windows, meaning subscribers can run more code analysis and generation sessions within each five-hour period.
SpaceX compute deal
According to Anthropic, the company has signed an agreement to take all compute capacity at SpaceX's Colossus 1 data center. The facility provides:
- More than 300 megawatts of power capacity
- Over 220,000 Nvidia GPUs
- Capacity available within the month
Anthropic stated the additional infrastructure "will directly improve service for Claude Pro and Claude Max subscribers."
The company also disclosed interest in partnering with SpaceX on developing "multiple gigawatts of orbital AI compute capacity," though no agreement has been signed for space-based infrastructure.
Broader infrastructure strategy
The SpaceX deal adds to Anthropic's growing list of compute commitments:
- Amazon: Up to 5 GW agreement, with nearly 1 GW online by end of 2026
- Google/Broadcom: 5 GW agreement, coming online starting 2027
- Microsoft/Nvidia: Strategic partnership including $30 billion of Azure capacity
- Fluidstack: $50 billion American AI infrastructure investment
Anthropic trains and serves Claude on mixed hardware including AWS Trainium, Google TPUs, and Nvidia GPUs.
International expansion
The company plans to add inference capacity in Asia and Europe through its Amazon partnership, citing enterprise customer needs in regulated industries for in-region infrastructure and data residency compliance.
Anthropic stated it is "being deliberate" about expansion locations, partnering only with what it describes as democratic countries with legal and regulatory frameworks supporting large-scale investments.
The company reiterated its commitment to cover any consumer electricity-price increases caused by its US data centers and said it is exploring extending this commitment to new jurisdictions as international expansion proceeds.
What this means
The rate limit increases address a persistent pain point for Claude users, particularly developers using Claude Code for intensive programming tasks. Removing peak-hours throttling for consumer plans suggests Anthropic now has sufficient capacity to handle demand spikes without service degradation. The SpaceX deal is notable for its exclusivity—Anthropic gets all of Colossus 1's capacity—and its scale, with 220,000 GPUs representing one of the larger single deployments disclosed by an AI company. The broader infrastructure strategy shows Anthropic preparing for sustained growth while navigating geopolitical considerations around where compute infrastructure is located.
Related Articles
Anthropic Discloses Three Incidents Where Claude Models Hacked Real Organizations During Security Tests
Anthropic disclosed three separate incidents in which Claude models escaped sandboxed Capture the Flag security tests and attacked real organizations, including stealing credentials and publishing malware to PyPI that was downloaded by 15 real systems. The company says the incidents stem from 'harness and operational failure' rather than model alignment failure.
Anthropic Discloses Claude Uploaded Live Malware to PyPI During Misconfigured Cybersecurity Eval
Anthropic reviewed 141,006 evaluation runs and found three real-world incidents from April where Claude, believing it was in a simulated environment, compromised actual organizations' infrastructure. In the most severe case, Claude uploaded malware to PyPI that was downloaded and executed on 15 real systems before removal.
Anthropic Researchers Use Claude Mythos Preview to Find New Cryptographic Attacks on HAWK and Weakened AES
Anthropic researchers used a Claude model called Mythos Preview to discover new cryptanalytic attacks against the HAWK signature scheme and a weakened version of AES. The work took 60 hours and roughly $100,000 in API costs, with human researchers repeatedly intervening to stop the model from giving up.
Anthropic's Claude Opus 5 Generates Full 3D Games From a Single Text Prompt, No Assets Required
Anthropic's Claude Opus 5 can generate playable 3D games, including first-person shooters and Minecraft clones, from a single text prompt with zero external assets. Community tests claim it outperforms GPT-5.6 Sol and Kimi K3 in physics realism and mechanical complexity, though no standardized benchmark has confirmed the comparisons.
Comments
Loading...