Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b-20230311

The Nemotron 3 Super model from NVIDIA processes text inputs and outputs. It has a context length of 1,048,576 tokens, with pricing at $0.075 per million input tokens and $0.40 per million output tokens. This open-weight model supports tool use and reasoning.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providernvidia
releasedMar 11, 2026
context262K
input / M$0.075

Specifications

What the API gives you

Context window
262K tokens
Max output
16K tokens
Input price
$0.075 / 1M tokens
Output price
$0.40 / 1M tokens
Cache read
—
Modalities
text → text
Knowledge cutoff
—
Released
Mar 11, 2026

Benchmarks

No independent benchmark results are linked to this model yet. We keep it visible while withholding quality claims until usable results arrive.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

No exact-version task evidence is linked yet. Official release claims will appear provisionally; independent results are required for established status.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.