impulse

Nemotron 3 Super 120B A12B

Open weights

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.

API id nemotron-3-super-120b-a12bReleased 11 Mar 2026 (Mar 2026)
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
262K
tokens
Max output
262K
tokens per reply
Hosts
2
2 listings
Released
Mar 2026
11 Mar 2026

Where to run it

2 hosts serve Nemotron 3 Super 120B A12B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
NVIDIA NIMInference
nemotron-3-super-120b-a12b
-
nemotron-3-super-120b-a12b
$0.30 / $0.90

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: NVIDIA Open Model License
Runs in about 296.7 GB of GPU memory
Runtimes: TGI, vLLM

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller NVIDIA models

No similar NVIDIA model keeps its key capabilities.

Other frontier labs

  • GPT-5.5 Pro
    OpenAI · on OpenAI
    $30.00 / $180.00
    Has every key capability
  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability

Open-weight picks

  • Command A Plus
    Cohere · on AIHubMix
    $2.50 / $10.00
    Has every key capability
  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability

Model line

Newer and older versions, at each lab's own price.

  1. UndatedNemotron 3.5 Super 120B A12BLatest$0.20 / $0.50
  2. Mar 2026Nemotron 3 Super 120B A12BThis pageNot listed

Call it

Using NVIDIA NIM's API.

Python
from litellm import completion

response = completion(
    model="nvidia_nim/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Nemotron 3 Super 120B A12B cost?

Its lowest listed price is at Nebius AI Studio: $0.30 per million input tokens and $0.90 per million output tokens.

Which APIs offer Nemotron 3 Super 120B A12B?

Nemotron 3 Super 120B A12B runs on 2 APIs: NVIDIA NIM and Nebius AI Studio.

What is Nemotron 3 Super 120B A12B's context window?

262K tokens, with up to 262K tokens in one reply.

Is Nemotron 3 Super 120B A12B being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Nemotron 3 Super 120B A12B?

Yes. Nemotron 3.5 Super 120B A12B is the newest model in this line.

When was Nemotron 3 Super 120B A12B released?

NVIDIA released it on 11 Mar 2026.

What is Nemotron 3 Super 120B A12B's API model id?

Use nemotron-3-super-120b-a12b with NVIDIA NIM.

Sources

Raw catalog entry for nemotron-3-super-120b-a12b on NVIDIA NIM
{
  "litellm_provider": "nvidia_nim",
  "mode": "chat",
  "source": "https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b.md",
  "supported_endpoints": [
    "/v1/chat/completions"
  ]
}