MA
SemiAnalysis MOTS: AI Chip Shortages, SpaceX, China, Neoclouds, and more!Matthew Berman25 Sept 2026
The chapter discusses OpenAI's custom AI chip, codenamed Jalapeño.
OJ
OpenAI Jalapeño Chip
by OpenAI
OpenAI's custom in-house AI accelerator chip, codenamed Jalapeño, discussed in industry analysis.
Updated EU status checked Last shown
OpenAI Jalapeño Chip at a glance
- What is OpenAI Jalapeño Chip?
- OpenAI Jalapeño Chip is a hardware from OpenAI. OpenAI's custom in-house AI accelerator chip, codenamed Jalapeño, discussed in industry analysis.
- Who makes OpenAI Jalapeño Chip?
- OpenAI Jalapeño Chip is made by OpenAI.
- Does OpenAI Jalapeño Chip work in the EU?
- Unverified. No explicit evidence found; the chip appears to be internal infrastructure and not a publicly available product. Last verified 14 Nov 2026.
- How much does OpenAI Jalapeño Chip cost?
- Pricing unknown. Not sold publicly; no pricing information found.
- Where was OpenAI Jalapeño Chip shown?
- In 3 creator videos by Matthew Berman, Matt Wolfe, AI Search. Most recently by Matthew Berman on 25 Sept 2026, at 19:04 in “SemiAnalysis MOTS: AI Chip Shortages, SpaceX, China, Neoclouds, and more!”.
Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
Jalapeño is the reported codename for a custom AI chip being developed by OpenAI. It appears in industry coverage, including a SemiAnalysis discussion on AI chip shortages, as part of OpenAI's effort to secure its own compute hardware alongside supply from third-party vendors.
No official OpenAI page, specification sheet or launch announcement was available when this entry was written. Technical details such as architecture, process node, memory, performance, manufacturing partner and deployment timeline are not confirmed here and are left unspecified.
The chip is understood to be intended for OpenAI's own infrastructure rather than as a product sold to outside customers, so there is no public pricing or purchase route.
Key features
- Custom AI chip codenamed Jalapeño
- Developed by OpenAI for its own compute needs
- Discussed in SemiAnalysis coverage of AI chip supply
- Specifications not publicly confirmed
3 moments
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
MA
AI News: OpenAI Made a Massive Move Against NVIDIAMatt Wolfe28 Aug 2026
OpenAI showed first results from its in-house inference chip, claiming up to 104x performance on open-weight models and a wider advantage on its internal frontier models. It is for inference only, not training.
AI
GPT 5.6, Mythos ban lifted, realtime avatars, Seedance 2.5, brain ultrasound: AI NEWSAI Search28 Jun 2026
OpenAI's first inference chip, made with Broadcom, developed in 9 months with help from OpenAI models. Early testing shows better performance per watt than current accelerators; gigawatt-scale deployment planned.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
OC
OpenAI custom AI chip
Hardware · OpenAI
OpenAI's in-house AI accelerator chip, developed to lower the cost of training and running its models; not publicly available.
UnverifiedHardware & Devices
Release date n/a
OI
OpenAI inference chip
Hardware · OpenAI
Custom AI inference chip announced by OpenAI and Broadcom, built to serve ChatGPT-style workloads faster and cheaper.
UnverifiedHardware & Devices
Release date n/a
OC
OpenAI Codex Hardware
Hardware · OpenAI
Codex-branded macro pad from OpenAI and Work Louder with programmable keys for shortcuts in the Codex coding tool.
UnverifiedHardware & Devices
15 Jul 2026
OC
OpenAI consumer AI hardware device
Hardware · OpenAI
Unreleased OpenAI consumer AI device; no specifications, price or launch date have been published.
UnverifiedHardware & Devices
Release date n/a
OO
OpenAI o1
Model · OpenAI
OpenAI's first reasoning model series, trained with reinforcement learning to think before answering; now deprecated in the API.
Available in EULanguage Models
12 Sept 2024API
LI
Ling-3.1-flash
Model · inclusionAI
Open-weights 560B hybrid-linear MoE reasoning model (25B active, 1M context) from inclusionAI, MIT licensed.
Available in EULanguage Models
13 Oct 2026Open source