Learn more
Learn more
July 23, 2026
Tokenomics in the Age of Agentic Inference
July 14, 2026
Tune it. Deploy it. Own it: Crusoe's next step in becoming the best cloud for open models
July 14, 2026
Introducing Self-Serve Deployments for production-scale inference
July 8, 2026
Frontier Agents at 10x lower cost: NVIDIA Nemotron 3 Ultra + LangChain Deep Agents on Crusoe Managed Inference

Our
Blog

Latest stories

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
All
General
Cloud
Black-and-white iceberg on a black background, most of its mass hidden underwater, illustrating the hidden cost of AI inference. Crusoe blog header reading "The inference iceberg."
July 23, 2026
Tokenomics in the Age of Agentic Inference
Nikhil Kaul
Stuart Pitts
All
No items found.
Comparing the GLM-5.2 run and two Claude Opus 4.8 runs solving the Wiz Day-One CTF.
July 23, 2026
Solving the Wiz Day-One CTF with Crusoe Managed Inference
Elazar Leibovich
Nir Levy
All
Cloud
Engineering
Isometric cloud, server racks, and storage disks representing Crusoe's managed inference infrastructure.
July 20, 2026
The open agent stack: Running Nous Research’s Hermes Agent on Crusoe Managed Inference
Emmanuel Acheampong
All
Cloud
General
2026 Gartner Magic Quadrant for AI Infrastructure placing Crusoe in the Visionaries quadrant
July 15, 2026
Crusoe named a Visionary because of its ability to execute and completeness of vision
Erwan Menard
All
Cloud
Engineering
Deployment config panel connecting to two GPU server racks, showing the one-click path from settings to a live deployment
July 14, 2026
Self-Serve Deployments: Predictable performance, without the infrastructure lift
Sydnee Mayers
Nir Levy
Peleg Yair
All
Cloud
Dot cluster shifting from white to yellow, illustrating a base model transformed into a fine-tuned model
July 14, 2026
Tune it. Deploy it. Own it: Crusoe's next step in becoming the best cloud for open models
Piyush Kadam
Nir Levy
Janaki Ram Goteti
All
Cloud
Graphic for the Self-Serve Deployments launch: dedicated inference endpoints now live in Crusoe Intelligence Foundry
July 14, 2026
Introducing Self-Serve Deployments for production-scale inference
Sydnee Mayers
Nir Levy
Peleg Yair
All
Cloud
Engineering
Isometric cloud and server illustration for Crusoe Managed Inference hosting the Nemotron 3 model family
July 8, 2026
Frontier Agents at 10x lower cost: NVIDIA Nemotron 3 Ultra + LangChain Deep Agents on Crusoe Managed Inference
Emmanuel Acheampong
All
Cloud
Engineering
Isometric illustration of GPU monitoring dashboards showing utilization charts, performance metrics, and a central GPU chip, rendered in Crusoe slate blue with hi-vis yellow accents
June 26, 2026
Debugging a GPU fleet shouldn't feel like detective work
Martin Cala
Vera Xiao
All
Cloud
Engineering
Artificial Analysis output speed leaderboard showing Crusoe ranked first at 449 tokens per second for Kimi K2.6/K2.7, ahead of Fireworks, Together AI, CoreWeave, and other inference providers.
June 24, 2026
430+ tokens per second: optimizing Kimi K2.6 and K2.7 for production
Alon Kejzman
Bar Hack
Omri Berkovitch
Omer Landau
All
Cloud
General
Crusoe and Linum logos side by side on a black banner, set against a macro photograph of lichen-covered rock
June 22, 2026
Better networking, 25% lower training costs: How Linum built a frontier video model on Crusoe
Jess Goldberg
All
Cloud
Engineering
Abstract technical illustration showing overlapping curved lines with hi-vis yellow node points on a dark background, representing system state reconciliation and parallel provisioning processes.
June 10, 2026
From the rack to ready: How Crusoe Provisioner gets every node to production
Alex Akesson
Hiren Panchasara
No results found

Scaling inference doesn’t need faster GPUs

Learn how to skip the inference bottleneck.

Download

Are you ready to build something amazing?

Contact us