Cerebras, the world’s fastest AI provider, and Core42, a G42 company specializing in sovereign cloud and AI infrastructure, have launched the global availability of OpenAI’s gpt-oss-120B model. Delivered via the Core42 AI Cloud and Compass API, the collaboration enables Cerebras inference at 3,000 tokens per second, unlocking enterprise-scale agentic AI capabilities.
Built on Cerebras’ CS-3 system and wafer-scale engine (WSE), the platform delivers real-time reasoning with ultra-low latency and radically lower cost-per-token compared to GPU-based systems. This breakthrough allows organizations to scale instantly from experimentation to full production deployments.
The gpt-oss-120B model offers unprecedented reasoning power, 128K token context windows, and advanced real-time capabilities for open-weight ecosystems. It supports enterprise applications such as semantic search, code execution, automation, and decision intelligence — transforming how businesses, researchers, and governments deploy AI at scale.
Key Benefits
- Agentic AI at scale: Enables reasoning-capable, performance-optimized AI systems for mission-critical workloads.
- Enterprise-grade performance: Handles the fastest and most demanding workloads globally.
- Industry-leading speed: Integrates seamlessly into reasoning, knowledge retrieval, and long-context generation workflows.
Trevor Cai, Head of Infrastructure at OpenAI, said: “Together with Cerebras and Core42, we’re making our best and most usable open model available at unprecedented speed and scale. This collaboration will give enterprises, researchers, and governments the ability to build real-time reasoning applications with extraordinary efficiency.”
Andrew Feldman, CEO and co-founder of Cerebras, emphasized that the partnership “delivers the world’s most capable open-weight models directly into the hands of enterprises, researchers, and governments in the Middle East and globally.”
Kiril Evtimov, CEO of Core42 and Group CTO of G42, added: “By running OpenAI gpt-oss on Cerebras hardware within Core42’s AI Cloud and Compass API, we are setting a new benchmark for performance, flexibility, and compliance in AI.”
With this collaboration, Cerebras and Core42 position themselves at the forefront of enterprise AI, combining speed, cost-efficiency, and compliance to power the next generation of reasoning-capable applications worldwide.
