Models Directory/nvidia/nemotron-ocr-v2
nvidiaCatalog Onlyfree endpoint

nemotron-ocr-v2

nvidia/nemotron-ocr-v2

Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.

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

Model Architecture & Limits

Canonical IDnvidia/nemotron-ocr-v2
Publisher / Originatornvidia
Model FamilyNemotron
ArchitectureHybrid detector-recognizer with document-level relational modeling <br> (RegNetX-8GF)
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.