Nemotron-3.5 Super-120b-a12b API Pricing Calculator

NVIDIA Nemotron 3.5 Super is an open-weight multimodal reasoning model for coding, autonomous agents, visual understanding, video analysis, and long-context workflows.

Nemotron-3.5 Super-120b-a12b, released 15 October 2026, is a multimodal model from NVIDIA. It pairs a 1,048,576-token context window with up to 262,144 tokens of output, taking text, audio, image, video and file input and returning text. Step-by-step reasoning is supported. It costs $0.20 per million input tokens through Perplexity.

Last updated Oct 18, 2026

Never miss an AI pricing or launch update

Get notified about new model launches, pricing changes, provider updates, deprecations, and cost-saving insights.

🔒 We respect your privacy. Unsubscribe anytime.

Model Details

Released
Oct 15, 2026
Context Length
1,048,576
Max Output
262,144
Modalities
Text Audio Image Video File → Text
Capabilities
Tool use Structured outputs Code execution Open weights
Hugging Face
nvidia/NVIDIA-Nemotron-3.5-Super-VL on Hugging Face (opens in a new tab)

Where is Nemotron-3.5 Super-120b-a12b a perfect fit?

Nemotron 3.5 Super combines a hybrid Mamba-Transformer MoE architecture with multimodal perception, configurable reasoning, and speculative decoding for efficient coding, document analysis, video understanding, and agentic automation. It is best suited for:
- Autonomous agents and multi-step tool workflows
- Software engineering and coding agents
- Long-context document and knowledge-base analysis
- Image and video understanding
- Visual tool use and GUI workflows
- Enterprise research and automation
- Retrieval-augmented generation
- Long-running interactive agent tasks
- Self-hosted multimodal AI applications

Quick Model Estimate

(USD 0.2000 per 1M tokens)
(USD 0.5000 per 1M tokens)

Your Nemotron-3.5 Super-120b-a12b Cost Estimate

💰 Total Cost

—

for 1000 input + 1000 output tokens

📥 Input (1000 × $0.200000) —
📤 Output (1000 × $0.500000) —

Cost Breakdown

📥 Input 📤 Output

Prices are watched for changes and checked against the provider's own page.

Pricing

Provider ↕
Modality ↕
Service Tier ↕
Input Price
(per 1M tokens) ↕
Output Price
(per 1M tokens) ↕
Cached Input
(per 1M tokens) ↕
Context Size ↕
View
Perplexity LogoPerplexityTextStandard$0.2000$0.5000$0.04001,048,576 tokens→

Other Models in the Nemotron-3.5 Family

Nemotron-3.5 Lightning-30b-a3b

Active

Reasoning · 1,048,576 context

FAQs about Nemotron-3.5 Super-120b-a12b

How much does Nemotron-3.5 Super-120b-a12b cost per 1M tokens?

Nemotron-3.5 Super-120b-a12b costs $0.20 per million input tokens, and $0.50 per million output tokens.

What does a typical workload cost with Nemotron-3.5 Super-120b-a12b?

1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $0.65 with Nemotron-3.5 Super-120b-a12b at its lowest rates. Use the calculator on this page for your own volumes.

Where can I use Nemotron-3.5 Super-120b-a12b?

Nemotron-3.5 Super-120b-a12b is available through Perplexity, from $0.20 per million input tokens.

What is Nemotron-3.5 Super-120b-a12b's context window?

Nemotron-3.5 Super-120b-a12b has a context window of 1,048,576 tokens, and returns up to 262,144 tokens in a single response.

What input types does Nemotron-3.5 Super-120b-a12b support?

Nemotron-3.5 Super-120b-a12b accepts text, audio, image, video and file input, and returns text.