{"id":"5251cd4c-1e27-4add-ac98-a76d3add4b46","slug":"nvidia-alpamayo","name":"NVIDIA Alpamayo","description":"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.","brainType":"foundation-model","isOpen":true,"maturityStage":"pilot","architecture":"Reasoning-based vision language action (VLA) models with chain-of-thought","reviewStatus":"reviewed","sources":[{"url":"https://nvidianews.nvidia.com/news/alpamayo-autonomous-vehicle-development","date":"2026-01-05","title":"NVIDIA Announces Alpamayo Family of Open-Source AI Models and Tools","sourceName":"NVIDIA Newsroom"},{"url":"https://blogs.nvidia.com/blog/open-models-data-tools-accelerate-ai/","title":"NVIDIA Unveils New Open Models, Data and Tools","sourceName":"NVIDIA"},{"url":"https://www.nvidia.com/en-us/solutions/autonomous-vehicles/alpamayo/","title":"NVIDIA Alpamayo","sourceName":"NVIDIA"},{"url":"https://developer.nvidia.com/drive/alpamayo","title":"NVIDIA Alpamayo","sourceName":"NVIDIA"},{"url":"https://nvidianews.nvidia.com/news/nvidia-alpamayo-2-super-robotaxis","date":"2026-03-16","title":"NVIDIA Launches Alpamayo 2 Super Reasoning Model for Robotaxis","sourceName":"NVIDIA"}],"keyFacts":[{"label":"Alpamayo family launch (primary NVIDIA)","value":"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)"},{"label":"Industry interest named by NVIDIA","value":"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)"},{"label":"Open AV model family","value":"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)."},{"label":"AlpaSim and driving data","value":"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)."},{"label":"Open AV reasoning models page","value":"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)."},{"label":"Newsroom launch framing","value":"NVIDIA's newsroom announcement presents Alpamayo as open-source AI models and tools to accelerate safe, reasoning-based autonomous vehicle development (NVIDIA Alpamayo news)."},{"label":"Open autonomous-driving model family","value":"NVIDIA presents Alpamayo as a family of open AI models and tools for reasoning-based autonomous vehicle development (NVIDIA Alpamayo developer page)."},{"label":"Perception and trajectory reasoning","value":"NVIDIA says Alpamayo 2 Super supports 360-degree perception, trajectory prediction, and chain-of-causation reasoning for robotaxis (NVIDIA Alpamayo 2 Super)."}],"aliases":[],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-08-09T14:40:23.334Z","updatedAt":"2026-10-09T22:00:50.985Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/nvidia-alpamayo","url":"https://registry.deploy.report/brains/nvidia-alpamayo","name":"NVIDIA Alpamayo","description":"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.","identifier":"5251cd4c-1e27-4add-ac98-a76d3add4b46","applicationCategory":"foundation-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"pilot","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":5,"primary_source_types":[]}}}