DEPLOYDatabase

Brain

NVIDIA Alpamayo

NVIDIA's open-source family of vision language action (VLA) models for autonomous vehicle development. Features chain-of-thought, reasoning-based decision-making that brings humanlike thinking to AV decisions. Models reason over complex driving scenes, verbalize decision logic, and support interpretable, auditable autonomy. Can be used as student backbone for automotive policy model distillation.

Foundation model · Maturity: Pilot · Open source

Machine-readable surfaces

Architecture

Reasoning-based vision language action (VLA) models with chain-of-thought

Key facts

Alpamayo family launch (primary NVIDIA)
NVIDIA's Jan 5 2026 CES newsroom release unveils the Alpamayo family of open AI models, simulation tools, and datasets for reasoning-based autonomous vehicle development. Alpamayo 1 is described as a 10-billion-parameter chain-of-thought reasoning VLA that uses video input to generate trajectories alongside reasoning traces, with open weights on Hugging Face. AlpaSim is an open-source AV simulation framework on GitHub, and Physical AI Open Datasets are stated to include 1,700+ hours of driving data (NVIDIA Newsroom)
Industry interest named by NVIDIA
The same release says mobility leaders including Lucid, JLR, and Uber, plus Berkeley DeepDrive, are showing interest in Alpamayo for reasoning-based AV stacks toward level 4. Quotes include Kai Stepper (Lucid), Thomas Muller (JLR), Sarfraz Maredia (Uber), and Wei Zhan (Berkeley DeepDrive). Treat partner interest as NVIDIA-stated at launch, not a completed OEM production census (NVIDIA Newsroom)
Open AV model family
NVIDIA describes Alpamayo as a family of open AI models, simulation tools, and datasets for reasoning-based autonomous-vehicle development. The release names Alpamayo 1 as a 10-billion-parameter reasoning VLA model that takes video input and generates trajectories with reasoning traces (NVIDIA Alpamayo).
AlpaSim and driving data
NVIDIA says the Alpamayo release includes the open-source AlpaSim closed-loop simulation framework and Physical AI Open Datasets containing more than 1,700 hours of driving data (NVIDIA open models and tools).
Open AV reasoning models page
NVIDIA's Alpamayo product page describes an open family of AI models, tools, and datasets intended for reasoning-based autonomous vehicle and robotaxi development (NVIDIA Alpamayo).
Newsroom launch framing
NVIDIA's newsroom announcement presents Alpamayo as open-source AI models and tools to accelerate safe, reasoning-based autonomous vehicle development (NVIDIA Alpamayo news).
Open autonomous-driving model family
NVIDIA presents Alpamayo as a family of open AI models and tools for reasoning-based autonomous vehicle development (NVIDIA Alpamayo developer page).
Perception and trajectory reasoning
NVIDIA says Alpamayo 2 Super supports 360-degree perception, trajectory prediction, and chain-of-causation reasoning for robotaxis (NVIDIA Alpamayo 2 Super).

Developed by (1)

Common questions

What is NVIDIA Alpamayo?
NVIDIA's open-source family of vision language action (VLA) models for autonomous vehicle development. Features chain-of-thought, reasoning-based decision-making that brings humanlike thinking to AV decisions. Models reason over complex driving scenes, verbalize decision logic, and support interpretable, auditable autonomy. Can be used as student backbone for automotive policy model distillation.
Who developed NVIDIA Alpamayo?
NVIDIA Alpamayo is credited to NVIDIA on the DEPLOY registry. Each developer attribution is verified via primary sources.
Is NVIDIA Alpamayo open source?
Yes. NVIDIA Alpamayo is recorded as open-source / open-weights on the DEPLOY registry, meaning model weights or source code are publicly available.
What type of AI is NVIDIA Alpamayo?
NVIDIA Alpamayo is a foundation model, built on a Reasoning-based vision language action (VLA) models with chain-of-thought architecture on the DEPLOY registry.
What is NVIDIA Alpamayo's maturity stage?
NVIDIA Alpamayo is at the pilot stage on the DEPLOY maturity ladder. Pilot stage means at least one named-customer trial deployment is verified.
Which robots run on NVIDIA Alpamayo?
No robot models on the DEPLOY registry are recorded as running NVIDIA Alpamayo. DEPLOY wires brain-to-model connections only when the wiring is verifiable from primary sources; absence may reflect pre-deployment or unverified manufacturer claims.

Sources (5)

  1. https://nvidianews.nvidia.com/news/alpamayo-autonomous-vehicle-development
  2. https://blogs.nvidia.com/blog/open-models-data-tools-accelerate-ai/
  3. https://www.nvidia.com/en-us/solutions/autonomous-vehicles/alpamayo/
  4. https://developer.nvidia.com/drive/alpamayo
  5. https://nvidianews.nvidia.com/news/nvidia-alpamayo-2-super-robotaxis
Methodology: Verified · 5 sources (no primary) · last reviewed 2026-10-09

Verification posture

Verified

Low confidence

Review state

Stable

Last reviewed 2026-10-09

Maturity + lifecycle

Maturity stage: pilot

Sources by quality tier

5
unclassified
Unclassified source

The framework is documented at /methodology. Corrections at /corrections. Reviewer: DEPLOY editorial team.

Methodology surface for NVIDIA Alpamayo.

Canonical ID 5251cd4c-1e27-4add-ac98-a76d3add4b46