nemotron-page-elements-v3

nvidia/nemotron-page-elements-v3

NVIDIA Build Card

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

Context Length

Not published

Input Pricing

Not published

Output Pricing

Not published

Recent Latency

No probes

Model Architecture & Limits

Canonical IDnvidia/nemotron-page-elements-v3

Publisher / Originatornvidia

Model FamilyNemotron

ArchitectureYOLOX <br> (DarkNet53 Backbone + FPN decoupled head (one 1x1 convolution + 2 parallel 3x3 convolutions: one for classification and one for bounding box prediction) <br>)

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

NVIDIA API Trial Terms of Service

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