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.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Nemotron 3 Super 120B A12B. Pricing starts at $0.075 per million input tokens and $0.400 per million output tokens. The model supports a context window of up to 262K tokens. API access is available through Nvidia.

Context Window
262K
tokens
Pricing
Input$0.075
Output$0.400
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Text only

Nemotron 3 Super 120B A12B is priced at $0.075 per million input tokens and $0.400 per million output tokens. It has a context window of 262,144 tokens. It is available from 1 provider, with DeepInfra the cheapest at $0.075 per million input tokens. Over the past ~90 days its cheapest input price has fallen 11.8%, from $0.085 to $0.075 per million tokens.

Pricing Comparison

Compare Nemotron 3 Super 120B A12B with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.075
$0.400
—
—
—
262,144
Try
$0.065
$0.260
—
—
—
1,000,000
Try
$0.070
$1.400
—
—
91.7
1,048,576
Try
$0.070
$0.280
—
—
—
160,000
Try
$0.070
$0.280
—
—
—
131,072
Try
$0.070
$0.070
—
—
—
8,192
Try
$0.070
$0.350
—
—
—
32,000
Try
$0.070
$0.140
—
47.6
20.8
16,384
Try
$0.074
$0.295
—
—
—
8,192
Try
$0.074
$0.295
—
—
—
8,192
Try
$0.075
$0.400
—
—
—
1,000,000
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.

1
Providers
$0.075
Cheapest Input/M
$0.400
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

1 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
DeepInfra
DeepInfra
Best Price
$0.075
$0.400
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

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 $0.000075 per 1,000 input tokens and $0.000400 per 1,000 output tokens.
Nemotron 3 Super 120B A12B is available from 1 provider. DeepInfra offers the best price.
DeepInfra offers Nemotron 3 Super 120B A12B at $0.075 per million input tokens.
Yes. Over the past ~90 days, the cheapest input price for Nemotron 3 Super 120B A12B has dropped 11.8%, from $0.085 to $0.075 per million tokens.
We compare Nemotron 3 Super 120B A12B with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Nvidia Models

See pricing for all Nvidia models.

View all Nvidia models →