Nemotron 3 Super 120B A12B API Pricing

Nemotron 3 Super 120B A12B pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Nemotron 3 Super 120B A12B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

100 long-document requests with 100,000 input and 2,000 output tokens each

Nemotron 3 Super 120B A12B features

• Function calling
• Reasoning

Use Nemotron 3 Super 120B A12B with LiteLLM

Call Nemotron 3 Super 120B A12B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="nebius/nvidia/nemotron-3-super-120b-a12b",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: nemotron-3-super-120b-a12b
    litellm_params:
      model: nebius/nvidia/nemotron-3-super-120b-a12b
      # credentials: see the provider's LiteLLM docs page

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "nemotron-3-super-120b-a12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Nemotron 3 Super 120B A12B FAQ

More NVIDIA models

• Nemotron 3 Nano Omni$0.06 / $0.24 per 1M tokens
• Nemotron 3 Nano 30B A3B$0.05 / $0.20 per 1M tokens
• Nemotron 3 Ultra$0.60 / $2.40 per 1M tokens
• Nemotron 3 120B A12B$0.50 / $1.50 per 1M tokens
• Nemotron 3.5 Lightning 30B A3B$0.0115 / $0.17 per 1M tokens
• Nemotron 3 Ultra 550B A55B$0.25 / $2.50 per 1M tokens
• Cosmos3 Super Reasoner$0.10 / $0.30 per 1M tokens
• Nvidia Nemotron 3 Nano 30B A3B$0.06 / $0.24 per 1M tokens