Skip to main content

One post tagged with "in-house-chip"

View all tags

OpenAI's In-House AI Chip Jalapeño Deep Dive: Taped Out in 9 Months, Inference Cost Cut 50%

· 9 min read
AI Hardware Analyst

On June 24, 2026, OpenAI and Broadcom jointly announced their first in-house AI inference chip, Jalapeño. This ASIC designed specifically for large language model inference went from design to tape-out in just 9 months and cuts inference cost by roughly 50%, marking OpenAI's transformation from a pure model company into a full-stack AI infrastructure provider.


1. Core conclusions (read this first)

DimensionJalapeñoCurrent GPU solutionAdvantage
Inference cost-50%Baseline✅ Half the cost
Performance per wattClearly superiorMost advanced accelerator✅ Energy-efficiency lead
Design cycle9 months~18 months✅ 2× faster
PositioningInference ASICTrain+inference GPUDedicated optimization
SupplyInternal onlyMarket purchase⚠️ Not for sale

One-line summary: Jalapeño is a key step in OpenAI's full-stack AI strategy, using in-house silicon to cut inference cost 50% while opening a new paradigm of "AI-assisted design of AI chips."


2. What is Jalapeño?

2.1 Basic information

ItemDetail
NameJalapeño (a chili pepper)
TypeApplication-specific integrated circuit (ASIC)
PositioningLarge language model inference
Announced2026-06-24
Taped outSep 2025 (est., 9-month rapid tape-out)
DeploymentEnd of 2026 (gigawatt-scale data centers)
PartnersBroadcom, TSMC, Celestica
ProcessTSMC 3nm
ArchitectureSystolic Array
HBM8 stacks (est. HBM3E or HBM4)

2.2 Why "Jalapeño"?

Jalapeño is a Mexican chili known for "medium heat, strong flavor." OpenAI's naming hints that the chip:

  • Medium heat: not the most aggressive architecture (vs Cerebras WSE), but effective enough
  • Strong flavor: strong presence in inference scenarios (50% cost reduction)
  • Appetizer: just "the first step of a multi-generation roadmap" (Broadcom CEO Hock Tan)

3. Deep technical analysis

3.1 9-month rapid tape-out: the new paradigm of AI-assisted chip design

Normally, designing an ASIC from scratch takes 1.5 to 2 years. Jalapeño went from initial design to manufacturing tape-out in just 9 months.

Key reason: deep software-hardware co-development

TechniqueDescription
AI-assisted architecture explorationOpenAI used its own frontier models (GPT-5.3-Codex-Spark) to explore chip architecture design space
AI power simulationAI models for power simulation and optimization
RL optimizationRL to optimize chip placement and routing
Broadcom silicon implementationBroadcom provides top-tier ASIC implementation (network, switch chip experience)

OpenAI President Greg Brockman said:

"We use the frontier models that serve our users to optimize the infrastructure that runs the models of the future."

3.2 Architecture optimized for inference

Unlike general-purpose GPUs, Jalapeño is an ASIC built from scratch around OpenAI's deep understanding of LLM inference workloads:

Architecture featureDescription
Reduce data movementCore principle is minimizing data movement (the main bottleneck in inference)
Balanced compute-memory-networkResource allocation optimized for inference, bringing real utilization closer to theoretical peak
High throughput + low latencyAims to combine the throughput of leading accelerators with the low latency of the fastest dedicated inference systems
Future model supportSupports not only current models (GPT-5, GPT-5.3) but adapts to next-gen inference needs

3.3 Full-stack platform: more than a chip

Jalapeño is a multi-generation compute platform, not just a chip:

ComponentSupplierDescription
Accelerator chipOpenAI design, TSMC fabTSMC 3nm, 8-stack HBM
Network switch chipBroadcom TomahawkHigh-speed interconnect (competes with NVIDIA NVLink)
Board, rack, systemCelesticaFull-rack solution
Software stackOpenAIDeep adaptation for GPT, Codex, Agent products

Deployment target: gigawatt-scale data centers

Broadcom CEO Hock Tan said:

"Jalapeño will begin deployment this year in gigawatt-scale data centers with Microsoft and other partners."


4. Performance and cost analysis

4.1 Inference cost cut 50%

Although OpenAI's official release was conservative on Jalapeño's cost savings — only stating its "performance per watt is substantially better than today's state of the art" without a specific percentage — per Bloomberg, Broadcom CEO Hock Tan revealed:

Early internal tests show Jalapeño achieves roughly 50% inference cost savings versus today's mainstream AI GPUs.

Significance for OpenAI:

ItemCurrent (GPU)JalapeñoSavings
Daily API callsHundreds of millionsHundreds of millions
Inference cost share~60-70% of operating cost~30-35%-50%
Annual compute spendBillions of dollarsHundreds of millionsSaves billions

4.2 Performance per watt clearly better than state of the art

OpenAI's announcement states:

"Jalapeño engineering samples have successfully run complex reinforcement-learning tasks such as GPT-5.3-Codex-Spark at target frequency and power; early tests show performance per watt substantially better than today's most advanced AI accelerators."

Comparison target: NVIDIA Blackwell (today's most advanced AI accelerator)

MetricJalapeñoNVIDIA BlackwellNote
Performance per wattClearly superiorBaselineOpenAI official statement
Inference latencyOn par with fastest dedicated inference systemsBaselineTarget
ThroughputOn par with leading acceleratorsBaselineTarget
TDPNot disclosed (est. 400-700W)700-1000WJalapeño possibly lower

5. Impact on the AI chip market

5.1 "De-NVIDIA-ification" accelerates

Jalapeño's launch is another footnote in big-tech's collective challenge to NVIDIA's market dominance:

VendorIn-house chipTypeStatusRelation to OpenAI
GoogleTPU v6e / IronwoodTrain+inference✅ CommercialGoogle Cloud supplies OpenAI
AmazonTrainium 3Training✅ LaunchedAWS supplies OpenAI
MicrosoftMaia 100Train+inference✅ LaunchedOpenAI exclusive partner
MetaMTIATrain+inference✅ Launched
AppleNeural EngineOn-device inference✅ Commercial
OpenAIJalapeñoInference🚧 Deploy end of 2026Internal + possibly sold to third parties

5.2 OpenAI is not about to fully "abandon" NVIDIA

Brockman admitted:

"We simply cannot get compute fast enough."

Currently OpenAI is simultaneously procuring chips from NVIDIA, AWS, AMD, and Cerebras; Jalapeño is a structural supplement to its explosive compute demand, not a replacement.

5.3 Possibly sold to third parties

Broadcom CEO Hock Tan specifically emphasized:

"This is just 'the start of a multi-generation roadmap'; OpenAI and Broadcom aim to jointly build gigawatt-scale compute clusters."

This means OpenAI may sell its hardware to third parties, provided it can secure enough supply from Broadcom and TSMC.


6. Jalapeño vs other in-house chips

MetricJalapeño (OpenAI)TPU v6e (Google)Trainium 3 (Amazon)Maia 100 (Microsoft)
Announced2026-06-242024Q4 20252023
TypeInference ASICTrain+inference TPUTraining ASICTrain+inference
ProcessTSMC 3nmTSMC 4nmTSMC 5nm (est.)TSMC 5nm (est.)
For sale❌ Internal only (maybe later)✅ GCP✅ AWS❌ Internal only
Design cycle9 months~18 months~18 months~18 months
AI-assisted design✅ First❌ No❌ No❌ No
Cost advantage-50% inference costOptimizedOptimizedOptimized

Key differences:

  • ✅ Jalapeño is the first AI chip designed with AI assistance
  • ✅ Jalapeño design cycle only 9 months (industry average 18 months)
  • ⚠️ Jalapeño not for sale (at least for now)

7. Future roadmap

7.1 Multi-generation chip platform

Jalapeño is just "the start of a multi-generation roadmap":

TimeEvent
End of 2026Jalapeño initial deployment (gigawatt-scale data centers)
2027Jalapeño v2 (est., architecture optimization)
2027-2028Jalapeño training version (est., challenging TPU/Trainium)
2028 and beyondGigawatt-scale compute cluster fully built

7.2 OpenAI full-stack AI infrastructure strategy

LayerOpenAI in-houseOutsourced/procured
Models✅ GPT-5, GPT-5.3, Codex
Chips✅ Jalapeño (inference)NVIDIA GPU, AWS Trainium, AMD GPU
Systems✅ With CelesticaMicrosoft Azure data centers
Network✅ Broadcom TomahawkMicrosoft Azure network
Cloud platform❌ NoneMicrosoft Azure (exclusive partner)

8. Industry reaction and expert views

8.1 Supportive views

ExpertView
Broadcom CEO Hock Tan"Jalapeño is just the start of a multi-generation roadmap; the goal is to jointly build gigawatt-scale compute clusters."
OpenAI President Greg Brockman"We use the frontier models that serve our users to optimize the infrastructure that runs the models of the future."
Industry insiders"Jalapeño's launch is another footnote in big-tech's collective challenge to NVIDIA's market dominance."

8.2 Skeptical views

ConcernDescription
Not for saleCurrently internal only; third parties cannot purchase, limited impact on NVIDIA's market share
Software ecosystemOpenAI must build its own software stack; competing with CUDA is hard
Supply capacityTSMC capacity is limited; can it meet OpenAI + Broadcom + other customers' demand?
Opaque performance dataOpenAI has not released specs (compute, memory, bandwidth, TDP), hard to assess objectively

9. Significance for developers

9.1 If OpenAI sells Jalapeño to developers in the future...

ScenarioCurrent (NVIDIA GPU)Future (Jalapeño)
Inference costBaseline-50%
Inference latencyBaselinePossibly lower
Software stackCUDA + TensorRTOpenAI API (possibly open-source stack)
Procurement difficultyHigh (export controls, supply shortage)Low (OpenAI direct supply)

9.2 Worth watching even if not sold

  • 50% inference cost cut forces NVIDIA, AMD, Intel to lower GPU prices
  • ✅ The AI-assisted chip design paradigm will be rapidly copied by the industry
  • ✅ The 9-month tape-out cycle becomes a new industry benchmark

10. Summary

DimensionAssessment
Technology innovation⭐⭐⭐⭐⭐ First AI chip designed with AI assistance, 9-month tape-out
Cost advantage⭐⭐⭐⭐⭐ 50% inference cost cut, billions saved annually
Strategic significance⭐⭐⭐⭐⭐ OpenAI transforms from pure model company to full-stack AI infrastructure provider
Market impact⭐⭐⭐⭐ "De-NVIDIA-ification" accelerates, big-tech in-house chip camp grows
Openness⭐⭐ Internal only for now, possibly sold to third parties later

Final recommendations:

  • 🇨🇳 China market: Keep watching Huawei Ascend, Cambricon MLU, Moore Threads MTT (Jalapeño not sold to China)
  • 🌍 International market: Watch whether Jalapeño is eventually sold externally and its impact on NVIDIA's market share
  • 💡 Developers: Watch for possible OpenAI API price cuts (50% inference cost cut may partially pass through)

References


Disclaimer: Some specs in this article are estimates, subject to OpenAI's official technical white paper. OpenAI will release a detailed performance white paper in the coming months.

Last updated: June 26, 2026