NVIDIA Nemotron 3.5 Super VL 120B API

NVIDIA Nemotron 3.5 Super VL 120B is a large language model by NVIDIA, available on the Venice API as nvidia-nemotron-3-5-super-vl-120b-a12b. It runs privately, with zero data retention.NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows.

NVIDIA Nemotron 3.5 Super VL 120B API pricing

Model ID	Variant	Privacy	Price
`nvidia-nemotron-3-5-super-vl-120b-a12b`	Standard	Private	$0.20 / $0.50 per 1M

NVIDIA Nemotron 3.5 Super VL 120B specifications

Spec	Value
Provider	NVIDIA
Released	Oct 16, 2026
Privacy	Private
Status	Stable
Open weights	Yes
Context window	256K tokens
Max output	100K tokens
Reasoning effort	Not adjustable
Served precision	FP4

How to use the NVIDIA Nemotron 3.5 Super VL 120B API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "nvidia-nemotron-3-5-super-vl-120b-a12b" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia-nemotron-3-5-super-vl-120b-a12b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

Related models

MiniMax M3.1 Flash API: $0.1875 / $0.75 per 1M
GLM 5.3 Flash API: $0.15 / $0.50 per 1M
Qwen 3.8 Flash API: $0.14 / $0.49 per 1M
MiMo-V2.6-Flash API: $0.175 / $0.35 per 1M

Explore

By modality