When will Jalapeño be available to use?

The chip is currently still being tested; no release date or availability timeline is stated in the announcement.

What is Jalapeño designed to do?

Jalapeño is specifically designed for inference—the process of running pre-built AI models in response to user commands. The company has emphasized its low operating cost when running real-time coding models.

Why is OpenAI building its own chip?

OpenAI says it has developed a deep understanding of its inference workload and wants to reduce dependence on Nvidia's GPUs. By controlling the entire stack—models, data centers, and hardware—the company can optimize each layer around the same goal: making its models faster, more reliable, and more affordable for users.

Back to articlesAI Stocks & Markets

AI Stocks & Markets

OpenAI has unveiled Jalapeño, its first custom chip for running AI models, co-designed with Broadcom to reduce reliance on Nvidia and improve the economics of serving AI responses to users.

TechCrunch AI3h ago4 min read

Key takeaway

OpenAI has unveiled Jalapeño, a custom inference chip developed with Broadcom, which early testing shows delivers better performance-per-watt than existing options. By building its own chip alongside models and data centers, OpenAI aims to lower the cost of serving AI responses to users and reduce its dependence on Nvidia.

Summaries like this, in your inbox every morning.

3 Key Points

What happened
OpenAI announced Jalapeño, a custom-built inference processor designed with Broadcom. The chip is still being tested, but early results show significantly better performance-per-watt than current alternatives, according to the company.
Why it matters
Running AI models to answer user requests (inference) is a major cost for OpenAI. A more efficient chip for this task could substantially lower operating expenses. Google and Amazon have already built similar custom chips for the same reason.
What to watch
Jalapeño is optimized specifically for inference workloads like real-time coding models. More demanding tasks such as pre-training are still expected to rely on Nvidia hardware. The company is integrating the chip as part of a broader strategy to control its entire stack—from model development to data center operations to hardware.

FAQ

When will Jalapeño be available to use?: The chip is currently still being tested; no release date or availability timeline is stated in the announcement.
What is Jalapeño designed to do?: Jalapeño is specifically designed for inference—the process of running pre-built AI models in response to user commands. The company has emphasized its low operating cost when running real-time coding models.
Why is OpenAI building its own chip?: OpenAI says it has developed a deep understanding of its inference workload and wants to reduce dependence on Nvidia's GPUs. By controlling the entire stack—models, data centers, and hardware—the company can optimize each layer around the same goal: making its models faster, more reliable, and more affordable for users.

Discussion

No comments yet. Be the first to share your thoughts!

Dell dominates AI server stocks with 242% gains year-to-date, while Super Micro Computer lags at 9% despite triple-digit revenue growth, raising questions about execution and valuation.

Yahoo Finance AI29m ago

OpenAI has unveiled Jalapeño, a custom AI chip made with Broadcom that matches Nvidia and Google's performance, marking its latest move to reduce reliance on limited-supply GPU suppliers.

The Verge AI29m ago

Sunrun surges 26% after announcing a 16-gigawatt virtual power plant partnership with Tesla and Renew Home to supply flexible energy capacity to data centers.

Yahoo Finance AI3h ago

Cisco stock hits a 52-week high on surging AI infrastructure orders, but analysts see limited upside at current prices after a sharp run.

Yahoo Finance AI3h ago

OpenAI and Broadcom have jointly developed Jalapeño, a custom chip designed specifically for running large language models, with deployment planned for late 2026 at gigawatt scale.

THE DECODER3h ago

Commvault and Microsoft partner to embed cyber resilience and AI protection directly into Azure, letting customers recover from attacks and data loss without separate tools.

Yahoo Finance AI6h ago

Stay ahead with AI news

Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.

Get Started Free

Free · takes 30 seconds · unsubscribe anytime

5 minutes a day. The AI essentials.

200+ sources · Email / LINE / Slack

Get it free →