LiteLLMModels

Nemotron Super 3 120B API Pricing

As of October 10, 2026, Nemotron Super 3 120B costs $0.15 per 1M input tokens and $0.65 per 1M output tokens on Amazon Bedrock. It has a 256,000-token context window and returns up to 32,000 tokens per response.

By NVIDIAModel ID nvidia.nemotron-super-3-120bPrices updated Checked
Input
$0.15 / 1M tokens
Output
$0.65 / 1M tokens
Context window
256,000 tokens
Max output
32,000 tokens
Providers
1
Added to LiteLLM
April 2026

Nemotron Super 3 120B pricing by provider

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

ProviderModel name in LiteLLMInputOutputContext
Amazon Bedrocknvidia.nemotron-super-3-120b$0.15$0.65256K
Amazon Bedrockeu-west-2bedrock/eu-west-2/nvidia.nemotron-super-3-120b$0.23$1.01256K
Amazon Bedrockus-gov-east-1bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b$0.18$0.78256K
Amazon Bedrockus-gov-west-1bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b$0.18$0.78256K
Amazon BedrockUS GovCloud cross-regionus-gov.nvidia.nemotron-super-3-120b$0.18$0.78256K

Other Nemotron Super 3 120B prices on Amazon Bedrock

Flex input$0.075 per 1M tokens
Flex output$0.325 per 1M tokens

What Nemotron Super 3 120B costs in practice

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

Amazon Bedrock$0.625

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

Amazon Bedrock$1.63

Nemotron Super 3 120B features

Use Nemotron Super 3 120B with LiteLLM

Call Nemotron Super 3 120B 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.

Python SDK
from litellm import completion

response = completion(
    model="nvidia.nemotron-super-3-120b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: nemotron-super-3-120b
    litellm_params:
      model: nvidia.nemotron-super-3-120b
      aws_region_name: os.environ/AWS_REGION_NAME
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "nemotron-super-3-120b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Nemotron Super 3 120B FAQ

How much does Nemotron Super 3 120B cost?

Nemotron Super 3 120B costs $0.15 per 1M input tokens and $0.65 per 1M output tokens on Amazon Bedrock.

What is the context window of Nemotron Super 3 120B?

Nemotron Super 3 120B has a 256,000-token context window and returns up to 32,000 tokens per response.

Which providers offer Nemotron Super 3 120B?

Nemotron Super 3 120B is available from Amazon Bedrock through LiteLLM, using the model name nvidia.nemotron-super-3-120b.

How do I call Nemotron Super 3 120B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="nvidia.nemotron-super-3-120b", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Nemotron Super 3 120B support?

Nemotron Super 3 120B supports function calling, structured output and reasoning. It does not support image input and audio input.

When did LiteLLM add Nemotron Super 3 120B?

Nemotron Super 3 120B was added to LiteLLM's model price file in April 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Amazon Bedrock.

Provider pages: Amazon Bedrock.