nvidia/nvidia-nemotron-120b-a12b/Released Mar 2026

Nemotron 3 Super

Hybrid Mamba-Transformer MoE with 1M context, optimized for agentic reasoning; 120B total, 12B active parameters.

Provider

nvidia

Modality

text-to-text

Released

Mar 2026

Pricing

$0.30 / 1M in$0.75 / 1M out

Ready to build with Nemotron 3 Super?

bash

curl -sSf -X POST https://hub.oxen.ai/api/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "nvidia-nemotron-120b-a12b",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'