NVIDIA Releases Alpamayo Open-Source AI Models for Autonomous Vehicles
NVIDIA unveiled the Alpamayo family of open AI models, simulation tools, and datasets at CES 2026 to accelerate safe, reasoning-based autonomous driving development.
At CES 2026, NVIDIA unveiled Alpamayo, a new family of open-source AI models, simulation tools, and datasets designed to accelerate the development of safe, reasoning-based autonomous vehicles. The release marks NVIDIA's largest open-source contribution to autonomous driving.
What's in the Alpamayo Release
The Alpamayo family includes several components:
- Alpamayo 1: An open reasoning Vision-Language-Action (VLA) model for autonomous driving
- AlpaSim: Simulation tools for testing autonomous vehicle behavior
- Physical AI Open Datasets: Training and evaluation data for AV development
- Integration tools: APIs and frameworks for incorporating Alpamayo into existing stacks
Reasoning-Based Autonomy
Unlike traditional autonomous driving systems that rely primarily on pattern matching, Alpamayo enables vehicles to reason about their environment:
- Long-tail scenarios: Handles unusual situations not well-represented in training data
- Explainable decisions: Can articulate why it made specific driving choices
- Adaptive behavior: Adjusts to novel road conditions and traffic patterns
- Safety reasoning: Explicitly considers safety implications of actions
First Open Reasoning VLA Model
NVIDIA claims Alpamayo 1 is the first open-source reasoning VLA model specifically designed for autonomous driving. The model combines:
- Vision: Understanding camera and sensor inputs
- Language: Processing instructions and explaining decisions
- Action: Generating appropriate vehicle control outputs
Why Open Source Matters
The open-source release enables several benefits for the AV industry:
- Democratized access: Smaller companies can build on state-of-the-art technology
- Faster iteration: Community contributions accelerate improvement
- Safety validation: Open models can be audited and verified
- Standardization: Common foundation reduces fragmentation
Integration with NVIDIA Ecosystem
Alpamayo integrates with NVIDIA's broader autonomous vehicle platform:
- NVIDIA DRIVE: End-to-end autonomous vehicle computing platform
- Isaac Sim: Robot simulation environment
- Omniverse: 3D simulation and digital twin platform
Availability
The Alpamayo models, tools, and datasets are available immediately on NVIDIA's developer portal and GitHub. The company is also offering integration support for automotive OEMs and tier-1 suppliers looking to incorporate the technology into their autonomous driving programs.
Related Articles
NVIDIA GTC 2026 Keynote: Jensen Huang Unveils Vera Rubin Platform and Six New Chips
NVIDIA CEO Jensen Huang opened GTC 2026 in San Jose with the formal unveiling of the complete Vera Rubin GPU platform — six new chips featuring 288 GB of HBM4 memory, 336 billion transistors, and 50 PetaFLOPS of FP4 performance. Over 30,000 attendees from 190 countries gathered for the AI industry's most anticipated annual event.
OpenAI Acquires Promptfoo to Strengthen AI Agent Security and Red-Teaming
OpenAI has agreed to acquire Promptfoo, the open-source AI security and red-teaming platform used by over 25% of the Fortune 500, in a deal that will integrate the tool directly into OpenAI's enterprise agent platform. The acquisition signals OpenAI's growing focus on safety infrastructure as it pushes deeper into autonomous AI agent deployment.
NVIDIA Releases Nemotron 3 Super: Open 120B-Parameter Model Targets Enterprise Agentic AI
NVIDIA has released Nemotron 3 Super, a 120-billion-parameter open-weights model built on a hybrid Mamba-Transformer architecture with a one-million-token context window. The model delivers 5x throughput improvements over its predecessor and is designed specifically for enterprise agentic AI workflows.