NVIDIA Buildmodels.m31a
Models Directory/nvidia/sparsedrive
nvidiaCatalog Onlyfree endpoint

sparsedrive

nvidia/sparsedrive
NVIDIA Build Card

End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.

Context Length
Not published
Input Pricing
Not published
Output Pricing
Not published
Recent Latency
No probes

Model Architecture & Limits

Canonical IDnvidia/sparsedrive
Publisher / Originatornvidia
Model FamilyNot published
ArchitectureCNN backbone \+ Multiple Transformers (SparseDrive uses a Resnet50 backbone for image feature extraction. The multi-head transformer-based architecture consists of:)
Context Window LimitNot published
Max Output TokensNot published
Endpoint Protocolnim-custom

Capabilities & Modal Surfaces

Chat Conversation✕ No
Tool / Function Calling✕ No
Reasoning / Thinking✕ No
Structured Output (JSON)✕ No
Vision / Multimodal✓ Yes
Audio Processing✕ No
License & Restrictions
**GOVERNING TERMS:** The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/
Commercial and research use permitted under governing model and API terms.