Nemotron 3 Super 120B A12B

nemotron-3-super-120b-a12b by NVIDIA Released March 12, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.085 / 1M
Output from
$0.4 / 1M
Cached input from
$0.3 / 1M
Context window
262K
Endpoints
3
from 2 providers
Regions
Monde, États-Unis

About Nemotron 3 Super 120B A12B

NVIDIA Nemotron 3 Super est un modèle MoE hybride ouvert comptant 120 milliards de paramètres, qui n'active que 12 milliards d'entre eux afin d'optimiser l'efficacité de calcul et la précision dans les applications multi-agents complexes.

Nemotron 3 Super 120B A12B est un modèle conversationnel développé par NVIDIA, disponible sur Eden AI via 3 endpoints chez 2 fournisseurs, à partir de 0,085 $ par million de tokens en entrée et 0,4 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 262K tokens.

Providers and prices

3 endpoints from 2 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
DeepInfra (États-Unis)Official−%deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
États-Unis
262K
$0.085$0.085
$0.4
$
ReasoningToolsJSONCacheVisionWeb
DeepInfra (États-Unis)Official−%deepinfra/nemotron-3-super-120b-a12b
États-Unis
262K
$0.085$0.085
$0.4
$
ReasoningToolsJSONCacheVisionWeb
NebiusOfficial−%nebius/nvidia/nemotron-3-super-120b-a12b
Monde
262K
$0.3$0.3
$0.9
$0.3
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.57 s
Nebius
Lowest latency
5.34 s
Nebius
Highest throughput
157.28 tok/s
Nebius
Best availability
100%
Nebius
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
DeepInfra (États-Unis)
s
s
s
tok/s
%
%
%
%
DeepInfra (États-Unis)
s
s
s
tok/s
%
%
%
%
Nebius
0.57 s
5.34 s
17.93 s
157.28 tok/s
100%
0%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Nemotron 3 Super 120B A12B with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Nemotron 3 Super 120B A12B

On Eden AI, prices for this model start at $0.085 per million input tokens and $0.4 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 262K tokens, depending on the endpoint.

3 endpoints from 2 providers, available in: Monde, États-Unis. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.57 s (Nebius) and the highest throughput was 157.28 tokens per second (Nebius).