Price Per TokenPrice Per Token
Nvidia

Nemotron 3 Super 120B A12B API Pricing 2026

Compare pricing, benchmarks, and providers for Nemotron 3 Super 120B A12B. Find the best value for your use case.

Get our weekly newsletter on pricing changes, new releases, and tools.

No bots, no big tech influence — join the new community for AI devs
8 Ways to Use Fewer Tokens
Last updated: April 19, 2026 at 08:26 AM

Overview

Nemotron 3 Super 120B A12B. Pricing starts at $0.090 per million input tokens and $0.450 per million output tokens. The model supports a context window of up to - tokens. API access is available through Nvidia.

Context Window
-
tokens
Pricing
Input$0.090
Output$0.450
Cached$0.100
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Text only

Pricing Comparison

Compare Nemotron 3 Super 120B A12B with 0 similar models by price.

Current Pricing (per 1M tokens)

1 models

Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.090
$0.450
-
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Nemotron 3 Super 120B A12B is available from multiple providers with different pricing and availability.

No multi-provider data available for this model

This model may only be available from a single provider

Community Rankings

How does Nemotron 3 Super 120B A12B perform? Vote based on your experience.

Cost vs. Quality

Compare Nemotron 3 Super 120B A12B's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try Nemotron 3 Super 120B A12B

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Nemotron 3 Super 120B A12B directly in your browser.

Open Playground

Frequently Asked Questions

Nemotron 3 Super 120B A12B costs $0.000090 per 1,000 input tokens and $0.000450 per 1,000 output tokens.

All Nvidia Models

See pricing for all Nvidia models.

View all Nvidia models →