MODEL Nvidia Last updated:

NVIDIA Isaac GR00T N1

Open Humanoid Foundation

NVIDIA's open vision-language-action model for humanoid robots — GR00T N1 (March 2025), N1.5, N1.7. Released Apache 2.0 with the full Isaac Lab + Isaac Sim ecosystem. The Cosmos Predict / Reason / Policy world models complement GR00T as simulation + planning upstream of the action model.

Try demo API Docs ↗
Cost
Free
Open weights — self-host
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out
Official ↗ GitHub ↗

Why it matters

Open VLA at the 2.2B parameter scale, integrated with the industry-standard simulator (Isaac Sim) and the dominant embedded compute platform (Jetson). NVIDIA is positioning to be upstream of every robotics company the way they are for every AI company.

Core Capabilities

Agent Workflows
Built for tool use and autonomous tasks.
Multimodal
Combines text, vision, and audio in one model.
Generative
Produces images, video, audio, or other media.
Vision
Understands images, scenes, and visual context.

Context Window

Context window not disclosed.

Availability

API
Not available
Product / App
Not available
Open Source
Released
Enterprise
—

Pricing Model

Free / self-host
Open weights — pay only for compute.
Self-host

What it feels like

  • Vision-language model from Nvidia — see the linked sources below for benchmark and review coverage
  • Tool-use and agent loops are the typical fit per the published model card
  • Vision and multimodal tasks are the typical fit per the published model card

Best use cases

  • Agent / tool-use workflows that match the model's published benchmarks
  • Vision tasks (charts, documents, images) per the model card
  • See the model spec and sources block for benchmarked use cases

Tools to try

NIM Microservices Build catalog

Not ideal for

  • Tasks far outside the modalities listed in this model's spec
  • Workflows where a more recent successor in the same family scores higher