LiteLLMModels

Nemotron 3 Ultra API Pricing

As of October 10, 2026, Nemotron 3 Ultra costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on Fireworks AI, with cache reads at $0.12 per 1M tokens. It has a 262,144-token context window and returns up to 32,768 tokens per response.

By NVIDIAModel ID fireworks_ai/nemotron-3-ultra-nvfp4Prices updated Checked
Input
$0.60 / 1M tokens
Output
$2.40 / 1M tokens
Cache read
$0.12 / 1M tokens
Context window
262,144 tokens
Max output
32,768 tokens
Providers
1
Added to LiteLLM
August 20, 2026

Nemotron 3 Ultra pricing by provider

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

ProviderModel name in LiteLLMInputOutputCache readContext
Fireworks AInvfp4fireworks_ai/nemotron-3-ultra-nvfp4$0.60$2.40$0.12256K
Fireworks AInvfp4fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4$0.60$2.40$0.12256K

Other Nemotron 3 Ultra prices on Fireworks AI

Priority input$0.75 per 1M tokens
Priority output$3.00 per 1M tokens

What Nemotron 3 Ultra costs in practice

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

Fireworks AI$2.40

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

Fireworks AI$6.48

Nemotron 3 Ultra features

Use Nemotron 3 Ultra with LiteLLM

Call Nemotron 3 Ultra 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="fireworks_ai/nemotron-3-ultra-nvfp4",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: nemotron-3-ultra
    litellm_params:
      model: fireworks_ai/nemotron-3-ultra-nvfp4
      api_key: os.environ/FIREWORKS_AI_API_KEY
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-3-ultra",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Nemotron 3 Ultra FAQ

How much does Nemotron 3 Ultra cost?

Nemotron 3 Ultra costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on Fireworks AI, with cache reads at $0.12 per 1M tokens.

What is the context window of Nemotron 3 Ultra?

Nemotron 3 Ultra has a 262,144-token context window and returns up to 32,768 tokens per response.

Which providers offer Nemotron 3 Ultra?

Nemotron 3 Ultra is available from Fireworks AI through LiteLLM, using the model name fireworks_ai/nemotron-3-ultra-nvfp4.

How do I call Nemotron 3 Ultra with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="fireworks_ai/nemotron-3-ultra-nvfp4", 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 3 Ultra support?

Nemotron 3 Ultra supports function calling, structured output and reasoning. It does not support image input.

When did LiteLLM add Nemotron 3 Ultra?

Nemotron 3 Ultra was added to LiteLLM's model price file on August 20, 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: Fireworks AI.

Provider pages: Fireworks AI.