NVIDIA Alpamayo

Reasoning AI for robotaxis and autonomous vehicles.

Overview
Video
Benefits
Open Platform
In-Car Software
In-Car Features
Getting Started
Resources
Next Steps

Overview
Video
Benefits
Open Platform
In-Car Software
In-Car Features
Getting Started
Resources
Next Steps

Overview

What Is NVIDIA Alpamayo?

NVIDIA Alpamayo is a family of reasoning AI models and software built for autonomous vehicles and robotaxis. It’s designed for complex, real-world driving, combining scene understanding with Chain of Causation reasoning to handle rare driving scenarios and generate explainable driving decisions.

The Alpamayo Open Platform brings together open models, simulation frameworks, and datasets to accelerate autonomous driving development. The Alpamayo Stack delivers full-stack driving software on NVIDIA Hyperion, combining in-vehicle reasoning AI with NVIDIA Halos safety technologies to support safe deployment.

Alpamayo 2 Super, The Frontier Open Model for Robotaxis and Autonomous Vehicles, Now Available

The frontier open reasoning model for autonomous vehicle and robotaxi development is here, commercially licensed and ready to build on.

Read the Blog Watch the Video

Generate Trajectories, Reasoning Traces, and Auto-Labels with NVIDIA Alpamayo 2 Super

This blog covers how AV developers can generate trajectories, causal reasoning traces, Meta-Actions, scene Q&A, and auto-labels across their own driving data.

Read the Blog

Video

Building Robotaxis and Autonomous Vehicles That Reason

NVIDIA Alpamayo Portfolio of Open Models for AV Development

This demo gives voice to Alpamayo’s internal reasoning, demonstrating what it could sound like if you could listen in, while the driver simply enjoys the ride.

Watch the Video

Benefits

What Does Alpamayo Bring to Robotaxi Development?

Reasoning-Based Autonomy

Unlike perception-only systems, Alpamayo empowers vehicles to explain why they act. Vision language action (VLA) models reason over complex driving scenes, verbalize decision logic, and support interpretable, auditable autonomy.

An Accelerated Path to Level 4

Alpamayo reduces the need to build core driving AI from scratch, shortening development cycles and accelerating industry progress toward Level 4 autonomy.

Open and Transparent AI

The Alpamayo Open Platform includes open model, frameworks, and datasets with training recipes to support fine-tuning on proprietary driving data. This helps accelerate model customization for different driving environments and vehicle programs.

Built for Safety and Scalability

The Alpamayo Stack combines in-vehicle reasoning AI with independent safety safeguards and NVIDIA Halos technologies to accelerate safe deployment on NVIDIA Hyperion.

Models and Frameworks

Core Components of the Alpamayo Portfolio

Alpamayo : Open Reasoning VLA Model

Alpamayo is built on NVIDIA Cosmos™ and processes multi-camera video, navigation inputs, and driving context to generate trajectories and Chain-of-Causation reasoning traces. It’s available in 10 billion parameters with Alpamayo 1 Nano and 1.5 Nano, and scales to 34 billion parameters with Alpamayo 2 Super.

Get Started on GitHub Download on Hugging Face

AlpaSim: Open Simulation Framework

An open-source closed-loop AV simulation framework, AlpaSim validates model decisions against real-world consequences, accelerating safety validation without scaling physical test fleets.

Get Started on GitHub

AlpaGym: Closed-Loop Reinforcement Learning

NVIDIA AlpaGym is a high-throughput closed-loop RL training framework, training AV models through continuous decision and observation cycles, producing models validated against the full complexity of real-world driving.

Read the How-to Guide

Physical AI Open Datasets: Real-World Driving Data

The largest open multi-sensor driving dataset available, Physical AI Open Datasets provide real-world driving data with Chain-of-Causation reasoning labels across 25 countries, purpose-built for long-tail scenario coverage.

Download on Hugging Face Developer Kit on GitHub

In-Car Software

Full-Stack Driving Software Built for Safety

From in-vehicle reasoning to runtime monitoring and validation, the NVIDIA Alpamayo Stack unifies every layer of driving software on NVIDIA Hyperion.

Halos SAFE

This safety assessment framework expands test coverage and accelerates validation through simulation-based testing.

Alpamayo

This is an in-vehicle reasoning model that interprets road scenes and generates driving trajectories to navigate complex, real-world scenarios.

Policy Evaluator and Safety Monitors

Runtime safeguards evaluate driving actions and support trajectory selection to reduce risk during autonomous operation.

Halos OS

This integrated system software combines system services with classical perception and planning capabilities to simplify driving software integration.

In-Car Features

Integrated Safety and Driving in Alpamayo Stack

Active Safety and Collision Avoidance

NCAP 2026 5-star compliant active safety automatically prevents collisions with vehicles, pedestrians, and cyclists through emergency braking, evasive steering, and 360-degree threat detection to protect what matters most.

Highway and Urban Driving

Address-to-address navigation combines route guidance with coordinated vehicle control through lane changes and intersections. Supervised hands-free operation extends driving assistance across highway and urban environments within defined operating conditions.

Driver and Occupant Monitoring

Supervised hands-free driving combines driver monitoring with escalating intervention if the driver becomes unresponsive, including a lane change to an adjacent emergency lane when feasible.

Automated Parking and Maneuvering

Full motion control automates entry into and exit from parallel, perpendicular, and angled parking spaces. Dynamic 360-degree views, obstacle warnings, and retrace assistance support visibility and maneuvering in confined spaces.

Starting Options

Getting Started With Alpamayo

Explore the Open Models

Start working with the Alpamayo 2 Super reasoning foundation model.

Download the model from GitHub and Hugging Face.
Generate trajectories and reasoning traces.
Build on open weights and Apache 2.0 code.

Start Developing

Post-Train and Optimize

Adapt Alpamayo to your own driving data and compress it for the edge.

Fine-tune it on your own driving data.
Post-train it with reinforcement learning.
Quantize the model for in-vehicle inference.

Get Recipes

Get in Touch

Talk to an NVIDIA AV specialist about moving from open model to in-vehicle deployment.

Deploy in-vehicle inference on DRIVE AGX Thor.
Plan your safety and certification path.
License Alpamayo for commercial production use.

Contact Sales

Resources

Explore the Latest in Automotive

Blogs
Videos
Sessions

View All Blogs

This is NVIDIA Alpamayo Thinking Out Loud

This demo gives voice to Alpamayo’s internal reasoning, showing what it could sound like if you could listen in, while the driver simply enjoys the ride.

Watch Now

In-Car Reasoning: AI That Drives, Explains Decisions, and Responds to Passengers

This video showcases four capabilities of NVIDIA Alpamayo: chain-of-thought, verbalized reasoning, natural language Q&A, and language instructions and commands.

Watch Now

How Autonomous Vehicles Learn to Reason With NVIDIA Alpamayo

See how open NVIDIA Alpamayo models, simulation frameworks, and physical AI datasets accelerate reasoning-based development for autonomous vehicles and self-driving cars.

Watch Now

View All Sessions

Next Steps

Ready to Get Started?

Use NVIDIA Alpamayo open models, frameworks, and datasets to develop reasoning-based autonomous driving.

Start Developing

Request a Consultation

Talk to an NVIDIA AV specialist about taking reasoning-based autonomous driving from Alpamayo models into production on NVIDIA DRIVE™.

Let’s Talk

Stay Informed

Get the latest news on NVIDIA automotive technologies, breakthroughs, and more.

Contact Us

This form is for automotive inquires only. For other inquiries, please click here.

Section

Section

First Name

Last Name

Business Email Address

Business Phone Number

Job Title

Organization / University Name

Interest Area

Website

Is Your Company a Startup?

Location

Address

City

State

State/Province

Postal/Zip Code

Industry

Preferred Language

Please provide a brief description of your product and business model.

Where do you stand within your product development? Please include the list of NVIDIA products you are using.

How can NVIDIA help you achieve your goals?

Send me the latest enterprise news, announcements, and more from NVIDIA. I can unsubscribe at any time.

NVIDIA Privacy Policy

I agree to the collection and processing of the above information by NVIDIA <span class="corporation-txt hidden">Corporation </span>for the purposes of research and event organization, and I have read and agree to <a href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/?deeplink=visiting-our-website" target="_blank">NVIDIA Privacy Policy</a>.

I agree that the above information will be transferred to NVIDIA Corporation in the United States and stored in a manner consistent with <a href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/?deeplink=visiting-our-website" target="_blank">NVIDIA Privacy Policy</a> due to necessities for research, event organization and corresponding NVIDIA internal management and system operation need. You may contact us by sending an email to <a href="mailto:privacy@nvidia.com">privacy@nvidia.com</a> to resolve related problems.