LLM Perks

Nemotron 3 Super

Free right now Frontier
ReasoningCodingTool useLong contextOpen weights

Nemotron 3 Super is a language model with 120B parameters from NVIDIA. It is currently free at 2 providers with up to 262K tokens of context. The model supports step-by-step reasoning, is suited to coding, supports tool calling. Its weights are open, so it can also run locally.

Developer
NVIDIA
Parameters
120B / 12B active
Context
262K tokens
Type
Text
License
Open weights

Where to use Nemotron 3 Super for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
NVIDIA Build
nvidia/nemotron-3-super-120b-a12b
— Free serverless inference for development; limits and model availability may change. No Open
UnoRouter
nemotron-3-super-120b-a12b:free
262K No-card free models use shared capacity and per-model limits; availability can change. No Open

Quick start

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for NVIDIA Build. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
12.8
GPQA Diamond
80.0%
Humanity's Last Exam
20.8%
Terminal-Bench Hard
28.8%
τ²-Bench
67.8%
Long context (LCR)
65.7%

Source: Artificial Analysis · Nemotron 3 Super 120B A12B (Reasoning)

Similar free models

FAQ

Is Nemotron 3 Super free?

Yes. As of October 31, 2026, Nemotron 3 Super is free at NVIDIA Build, UnoRouter. Each provider has its own limits — see the table above.

What is the context window of Nemotron 3 Super?

The largest context among free routes is 262,144 tokens. Some providers cap it lower.

How do I call Nemotron 3 Super via API?

Use any OpenAI-compatible client with base URL https://integrate.api.nvidia.com/v1, model ID nvidia/nemotron-3-super-120b-a12b, and a NVIDIA Build key.

How good is Nemotron 3 Super?

Artificial Analysis Intelligence Index: 12.8, GPQA Diamond: 80%. For comparison, the strongest free model in the catalog right now is GLM 5.3 Flash.

Is Nemotron 3 Super open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.