.jpg)
Cerebras Systems has introduced its API Certification Program, partnering with Dataiku, Vercel, Portkey, and TrueFoundry to deliver ultra-fast AI inference, enhancing enterprise AI adoption with up to 70x faster performance than GPU-based solutions.
Cerebras launches API Certification Program with leading AI platforms.
Partners include Dataiku, Vercel, Portkey, and TrueFoundry.
Offers sub-50 ms inference speeds, 70x faster than GPU solutions.
Integrations enable secure, scalable AI deployment for enterprises.
Hugging Face and OpenRouter enhance developer access and cost efficiency.
Over 200 startups have reduced AI costs by 40% with Cerebras.
Cerebras Systems, a pioneer in generative AI, announced its API Certification Program on September 10, 2025, in Sunnyvale, California. The program integrates Cerebras’ industry-leading AI inference capabilities, which deliver up to 70x faster performance than GPU-based solutions, with leading platforms like Dataiku, Vercel, Portkey, and TrueFoundry. These partnerships aim to democratize ultra-fast AI inference, enabling enterprises to scale AI workloads seamlessly while maintaining security and compliance.
Cerebras’ integration with Dataiku’s Universal AI Platform leverages its LLM Mesh to provide enterprise data teams with access to the world’s fastest AI inference through a secure API gateway. “With Dataiku, customers have the freedom to run enterprise AI on top of any tech stack—and now they gain the ability to choose Cerebras for inference compute at unprecedented speed,” said Jed Dougherty, VP of Platform Strategy at Dataiku. This alliance streamlines deployment, enhances model accuracy, and supports new AI use cases with Dataiku’s agnostic architecture and Cerebras’ Wafer-Scale Engine (WSE).
Partnering with Portkey, the world’s most popular open-source AI Gateway, Cerebras delivers unmatched inference speed and cost-efficiency, achieving over 1,100 tokens per second with 99.99% uptime. “Cerebras is one of the few inference providers in the market with a rare combination of extremely low latencies, high uptime, and reasonable costs,” said Portkey CEO Rohit Agarwal. The integration provides enterprises with observability, cost management, and guardrails, enabling faster production deployment.
Cerebras’ integration with TrueFoundry’s AI Gateway offers unified access to its inference capabilities via OpenAI-compatible APIs. “By integrating Cerebras with TrueFoundry’s AI Gateway, we’re enabling organizations to combine breakthrough performance with the controls and flexibility they need to confidently run AI in production,” said Anuraag Gutgutia, co-founder of TrueFoundry. Features like rate limiting and on-prem deployment ensure governance and data sovereignty for enterprise AI workloads.
Cerebras’ partnership with Vercel AI Cloud simplifies high-performance AI inference for web developers. “By connecting Cerebras’ inference infrastructure with our AI SDK and AI Gateway, developers gain the tools to build ultra-responsive, production-ready applications without complexity,” said Harpreet Arora, AI Product Lead at Vercel. This integration enables real-time content personalization and conversational interfaces, streamlining workflows through Vercel’s AI SDK and Gateway.
Building on collaborations with Hugging Face and OpenRouter, Cerebras enhances developer access with sub-50 ms responses and up to 50% lower per-token costs. “We are thrilled to add these world class partners to our ecosystem,” said Alan Chhabra, EVP of Worldwide Partners at Cerebras. Over 200 startups and mid-market customers have reduced AI infrastructure costs by 40% and accelerated model iteration by 5x, showcasing the program’s transformative potential.
Cerebras Systems is a team of pioneering computer architects, computer scientists, deep learning researchers, and engineers of all types. We have come together to accelerate generative AI by building from the ground up a new class of AI supercomputer. Our flagship product, the CS-3 system, is powered by the world’s largest and fastest commercially available AI processor, our Wafer-Scale Engine-3. CS-3s are quickly and easily clustered together to make the largest AI supercomputers in the world, and make placing models on the supercomputers dead simple by avoiding the complexity of distributed computing.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.