Nemotron 3 Super 120B-A12B API

nvidia/nemotron-3-super-120b-a12b
A hybrid Mixture-of-Experts reasoning model that punches far above its active parameter count — running on just 12 billion active weights while drawing on the depth of 120 billion total parameters. Built for the realities of production-grade agentic systems.
Context
262K tokens
Input
$0.123786 / 1M tokens
Output
$0.61893 / 1M tokens
Released
Apr 30, 2026

How to use Nemotron 3 Super 120B-A12B API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to nvidia/nemotron-3-super-120b-a12b.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "nvidia/nemotron-3-super-120b-a12b",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/nemotron-3-super-120b-a12b","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Nemotron 3 Super 120B-A12B API Pricing

TypePrice
Input
$0.123786 / 1M tokens
Output
$0.61893 / 1M tokens

Nemotron 3 Super 120B-A12B Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
GPQA Diamond
79.2%
Google-proof graduate science questions (hardest subset)SourceJuly 12, 2026
Intelligence
13.6
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
37.7
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Nemotron 3 Super 120B-A12B vs other models

ModelInputOutputContextBest for
$0.123786 / 1M tokens
$0.61893 / 1M tokens
262K tokens
Coding + agents
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Nemotron 3 Super 120B-A12B has a 262,144 tokens context window and can return up to 262,144 tokens.

Nemotron 3 Super 120B-A12B takes text as input and returns text.

Use nvidia/nemotron-3-super-120b-a12b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Nemotron 3 Super 120B-A12B became available on April 30, 2026.

Nemotron 3 Super 120B-A12B is priced at input $0.123786 / 1M tokens, output $0.61893 / 1M tokens.

Yes, Nemotron 3 Super 120B-A12B can stream responses as they are generated.

Nemotron 3 Super 120B-A12B was built by NVIDIA.

Yes, it supports function calling along with parallel tool calls.

Yes, structured output is listed as a supported feature and capability.

Start building with Nemotron 3 Super 120B-A12B

Get API Key
1000+ models, one API.