New Platform Integrations with Dataiku, Vercel, Portkey and TrueFoundry Accelerate Enterprise AI Adoption
SUNNYVALE, Calif.–(BUSINESS WIRE)–Cerebras Systems, the pioneer in accelerating generative AI, today introduced its API Certification Program, with new strategic partnerships with leading API gateway and AI platform providers Dataiku, Vercel, Portkey, and TrueFoundry. These integrations bring Cerebras’ industry-leading AI inference speeds—up to 70x faster than GPU-based solutions—directly to enterprise developers through unified, secure gateway platforms.
Cerebras today partners with Hugging Face to deliver blazing-fast inference via the Hugging Face Hub, empowering over five million developers with sub-50 ms responses. Integration with OpenRouter offers flexible, pay-per-token access for rapid prototyping and scalable deployment.
API Certification Partner Program
The Cerebras API Certification Partner Program’s core objective is to democratize ultra-fast AI inference across the enterprise stack. By certifying API providers who meet strict performance, security, and operational criteria, Cerebras ensures that end users can rely on sub-50 ms inference at scale. Certified partners benefit from technical enablement, co-marketing, and a clear path to evolving from basic integration to full-stack, production-ready solutions.
Certified by Cerebras
- Technical integration, optimization, and observability.
- Solution architect and enterprise support.
- Co-developed reference architectures and joint customer proof-of-concepts.
Dataiku LLM Mesh Integration
Cerebras has integrated with Dataiku, The Universal AI Platform™, leveraging its LLM Mesh capabilities as a premier inference provider, giving enterprise data teams direct access to the world’s fastest AI inference through Dataiku’s secure API gateway. By combining Dataiku’s flexible, governed platform with Cerebras’ leading AI compute, organizations can now scale AI workloads with unmatched speed, while maintaining control, compliance, and business alignment.
The alliance addresses a growing need in the enterprise AI landscape: how to scale workloads seamlessly, improve model accuracy, and unlock new use cases — all while streamlining deployment and reducing infrastructure complexity.
Dataiku’s agnostic architecture ensures compatibility across all major cloud, data, and AI ecosystems, while Cerebras delivers the world’s fastest AI inference and training performance through its revolutionary Wafer-Scale Engine (WSE). Together, the companies are delivering end-to-end capabilities for enterprise AI at scale.
“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. “That means faster iteration, lower latency, and the agility to deliver AI innovation at enterprise scale, all within Dataiku’s single, governed platform.”
Portkey AI Gateway
Cerebras has partnered with Portkey to give unmatched inference speed & cost-efficiency to enterprises deploying production AI. Portkey is the world’s most popular open-source AI Gateway, and the partnership puts Cerebras’ inference engine to be readily-used by companies that are looking for 99.99% uptime from their inference providers with incredible throughput of more than 1,100 tokens/sec.
Having Cerebras on Portkey means that enterprise platform teams get a central overview of how different teams & products are leveraging Cerebras for their use cases, with complete observability, cost-management, and guardrails built in, which allow companies to go to production much faster.
“Cerebras is one of the few inference providers in the market with a rare combination of 3 important traits: (1) Extremely low latencies, (2) Extremely high uptime, and (3) Reasonable costs!” Portkey’s CEO Rohit Agarwal said. “We are excited to bring Cerebras onto Portkey for our enterprise customers and give them a turnkey solution to get secure, scalable AI on tap.”
TrueFoundry AI Control Plane
Cerebras has integrated with TrueFoundry’s enterprise AI Gateway and control plane, providing organizations with unified access to Cerebras inference through OpenAI-compatible APIs. The partnership enables enterprises to deploy, govern, and monitor Cerebras-powered AI workloads alongside other LLM providers through a single management interface.
TrueFoundry’s advanced features including rate limiting, cost controls, and on-prem deployment options complement Cerebras’ performance advantages, creating a comprehensive solution for production AI applications. The integration supports both cloud and VPC deployment models, ensuring data sovereignty requirements are met.
“Our goal at TrueFoundry is to make it simple for enterprises to adopt cutting-edge AI without compromising on governance or security,” said Anuraag Gutgutia, co-founder of TrueFoundry. “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.”
Vercel AI Cloud
Cerebras is now integrated with Vercel AI Cloud, making it easier than ever for developers to bring high-performance AI inference into their web applications. By combining Cerebras’ wafer-scale infrastructure with Vercel’s AI SDK and AI Gateway, developers can seamlessly deploy advanced generative AI features, such as real-time content personalization, image generation, and conversational interfaces, at global scale.
The integration streamlines workflows through Vercel’s AI SDK for intuitive model orchestration and the AI Gateway for efficient request management, routing, and observability. This ensures that developers can instantly access Cerebras inference endpoints while focusing on building rich, production-ready experiences without managing backend infrastructure.
“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. “Together, we’re making advanced generative models accessible to every web application, anywhere in the world.”
World Class Leading Partnerships
These partnerships build upon Cerebras’ existing collaborations with Hugging Face and OpenRouter, creating a comprehensive ecosystem of developer tools and enterprise platforms.
Hugging Face integration showcases remarkable performance improvements, with models like Llama 3.3 70B achieving over 2,200 tokens per second—70 times faster than GPU-based solutions. The partnership has enabled breakthrough applications in conversational AI, code generation, and agentic systems that require chaining multiple LLM calls in real-time.
OpenRouter now delivers developers on-demand access to Cerebras inference capabilities, empowering teams to run up to 70× larger context windows at sub-5 ms latency and scale production workloads with usage-based pricing that drives up to 50% lower per-token costs compared to GPU alternatives. Since launch, over 200 startups and mid-market customers have reduced their AI infrastructure spend by an average of 40% while accelerating model iteration cycles by 5×.
“We are thrilled to add these world class partners to our ecosystem as we launch the Cerebras API Certification Partner Program,” said Alan Chhabra, EVP of Worldwide Partners at Cerebras. “By integrating with leading API gateways and AI platforms, we’re eliminating infrastructure barriers that have historically limited organizations’ ability to deploy cutting-edge AI at scale. Our partners provide the governance, security, and operational controls enterprises demand, while Cerebras delivers the breakthrough performance that transforms what’s possible with AI applications.”
Cerebras inference through Dataiku LLM Mesh, TrueFoundry AI Control Plane, Portkey AI Gateway and Vercel is available immediately for enterprise customers. Organizations can access these integrations through their existing platform subscriptions or contact Cerebras directly for implementation support.
About Cerebras Systems
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. Cerebras Inference delivers breakthrough inference speeds, empowering customers to create cutting-edge AI applications. Leading corporations, research institutions, and governments use Cerebras solutions for the development of pathbreaking proprietary models, and to train open-source models with millions of downloads. Cerebras solutions are available through the Cerebras Cloud and on-premises. For further information, visit cerebras.ai or follow us on LinkedIn, X and/or Threads.
Contacts
Media Contact
[email protected]
