NVIDIA Buildmodels.m31a
Models Directory/meta/llama-3.2-11b-vision-instruct
metaCatalog Onlyfree endpoint

llama-3.2-11b-vision-instruct

meta/llama-3.2-11b-vision-instruct
NVIDIA Build Card

Cutting-edge vision-language model exceling in high-quality reasoning from images.

Context Length
131,072 tokens
Input Pricing
$0.18 / 1M
Output Pricing
$0.18 / 1M
Recent Latency
No probes

Model Architecture & Limits

Canonical IDmeta/llama-3.2-11b-vision-instruct
Publisher / Originatormeta
Model FamilyLlama 3.2
ArchitectureDiffusion Transformer (DiT)
Context Window Limit131,072 tokens
Max Output Tokens4,096 tokens
Endpoint Protocolopenai-chat

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.