streampetr

nvidia/streampetr

NVIDIA Build Card

StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.

Context Length

Not published

Input Pricing

Not published

Output Pricing

Not published

Recent Latency

No probes

Model Architecture & Limits

Canonical IDnvidia/streampetr

Publisher / Originatornvidia

Model FamilyNot published

ArchitectureCNN backbone + Sparse Query-Based Transformer (streamPetr utilizes a standard image backbone (ResNet50 or Vision Transformer in varying configurations) to extract multi-view features from input camera images. These features are then processed by a Transformer-based detection head, which follows a sparse query design inherited from the PETR series. The architecture innovates with several modules:)

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 Open Model License Agreement](https://www.nvidia.com/e

Commercial and research use permitted under governing model and API terms.