AI & MACHINE LEARNING AI INFRASTRUCTURE

OpenAI Launches Jalapeño Chip and Secures Major HP Deal

TM
Techmediaglobal
| 5 min read
9 Months
CHIP DEVELOPMENT TIME
2
HARDWARE PARTNERS
Feb 2026
FRONTIER LAUNCH DATE
1st
OPENAI CUSTOM CHIP

OpenAI is scaling on two fronts at once: unveiling Jalapeño, its first custom AI chip, built with Broadcom and Celestica in just nine months, while landing HP as one of the first major enterprise customers for its new agent fleet-management platform, OpenAI Frontier.

Unveiling Jalapeño: Built in Just Nine Months

Broadcom presented OpenAI's first AI chip, named Jalapeño, last week, delivered to OpenAI CEO Sam Altman and President Greg Brockman by Broadcom President and CEO Hock Tan and President Charlie Kawwas.

OpenAI designed the chip around its own understanding of LLM fundamentals, with Broadcom and Celestica contributing to chip implementation, board and rack system integration, networking, and production systems. The entire process took just nine months, with OpenAI's own models helping speed up the design work itself.

Under the Hood of Jalapeño

Jalapeño is designed with the flexibility to work across all large language models, guided by OpenAI's insight into the inference needs of current and future frontier AI. Richard Ho, who leads OpenAI's hardware programme, says the team optimized the architecture around the kernels, memory movement, networking, and serving patterns that matter most for frontier models.

Engineering samples are already running ML workloads in the lab at production target frequency and power, including the GPT‑5.3‑Codex‑Spark model.

"Jalapeño is part of our long-term full-stack infrastructure strategy to make compute more abundant, resulting in AI which is faster, more reliable, more affordable for people and businesses and can be used to solve more important problems."

— Greg Brockman, President and Co-Founder, OpenAI

What Is OpenAI Frontier?

Launched by OpenAI in February, Frontier is a fleet-management platform designed to build, deploy, manage, and monitor teams of AI agents across large organizations. It was created to bridge what OpenAI calls the "AI opportunity gap": the disconnect between highly capable AI models and the messy, fragmented data systems found inside massive corporations.

HP began using Frontier when it launched in February, trialling agentic capabilities, platform components, security, and enterprise integrations before moving toward customer- and partner-facing deployment, employee productivity, and software development use cases.

HP Bets on Frontier Across Chat, Voice and Retail

HP is using Frontier to scale its customer support and digital operations, becoming one of the first global enterprises to adopt the platform with the goal of using specialized AI agents to unify its fragmented commercial touchpoints into a single network.

"With the use of Frontier platform, HP is planning to build a more consistent experience across store, partner, chat and voice experiences, giving customers and partners faster ways to get answers, complete routine workflows and move toward resolution," said Prakash Arunkundrum, Chief Strategy and Transformation Officer at HP.

"HP is showing what enterprise transformation looks like when AI becomes an operating layer, connected to the systems and workflows where work already happens," added Denise Dresser, Chief Revenue Officer at OpenAI, noting HP has turned early value from OpenAI's APIs and tools like ChatGPT and Codex into repeatable systems.

Key Takeaways

  • OpenAI unveiled Jalapeño, its first custom AI chip, built with Broadcom and Celestica in just nine months.
  • Jalapeño is optimized for the kernels, memory movement, networking, and serving patterns that matter most for frontier AI workloads.
  • Engineering samples are already running production-grade workloads, including the GPT-5.3-Codex-Spark model.
  • HP has become one of the first major enterprise customers for OpenAI Frontier, its fleet-management platform for AI agents.
  • HP plans to use Frontier to unify customer experiences across store, partner, chat, and voice channels.
  • Together, the chip and the Frontier deal position OpenAI as both a model developer and a foundational infrastructure provider for the autonomous enterprise.
Tags: OpenAI Jalapeño Chip AI Chips Broadcom HP OpenAI Frontier AI Agents Enterprise AI