ZMIME
NVIDIA · Released Mar 11, 2026

Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads.

  • Open weights
  • Reasoning
  • Tool calling
Capability
—No ECI score yet
Input
$0.20per 1M tokens
Output
$0.80per 1M tokens
Context
262K262K max output
Pricing

What it costs

Input
$0.20per million tokens
Output
$0.80per million tokens
Blended (3:1)
$0.35cheaper than 68% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.80
Team assistant25M input + 5M output tokens$9.00
Production app250M input + 50M output tokens$90.00

Official Nvidia API price, as listed on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for Nemotron 3 Super 120B A12B yet.

Specifications

The details

Lab
NVIDIA
Released
Mar 11, 2026
Context window
262,144 tokens
Max output
262,144 tokens
Inputs
Text
Output
Text
Reasoning
Can be switched on or off
Tool calling
Yes
Structured output
No
Weights
Open weights
API model ID
nvidia/nemotron-3-super-120b-a12bon Nvidia
Availability
19 API providerslisted on models.dev

Nvidia model documentation

Same lab

More from NVIDIA

Questions

About Nemotron 3 Super 120B A12B

How much does Nemotron 3 Super 120B A12B cost?

Nemotron 3 Super 120B A12B costs $0.20 input / $0.80 output per million tokens (official Nvidia API price). At a 3:1 input-to-output mix that is $0.35 per million tokens, cheaper than 68% of the 360 priced models we track.

What is the context window of Nemotron 3 Super 120B A12B?

Nemotron 3 Super 120B A12B accepts up to 262,144 tokens per request and can write up to 262,144 tokens in one response.

How good is Nemotron 3 Super 120B A12B?

Epoch AI has not published a Capabilities Index score for Nemotron 3 Super 120B A12B yet.

Is Nemotron 3 Super 120B A12B open source?

Yes. NVIDIA publishes the weights, so it can be downloaded and self-hosted.

What inputs does Nemotron 3 Super 120B A12B support?

Nemotron 3 Super 120B A12B accepts text and replies in text. It is a reasoning model, supports tool calling.

When was Nemotron 3 Super 120B A12B released?

NVIDIA released Nemotron 3 Super 120B A12B on Mar 11, 2026.

What are the best alternatives to Nemotron 3 Super 120B A12B?

The closest current models from other labs on capability, price and release date are Mercury 2 (Inception, $0.25 / $0.75), Trinity Large Thinking (Arcee AI, $0.25 / $0.80), Mistral Small 4 (Mistral AI, $0.15 / $0.60) and Seed 1.8 (ByteDance Seed, $0.119 / $1.19).