# Fw Nemotron 3 Ultra API Pricing

As of October 10, 2026, Fw Nemotron 3 Ultra costs $0.66 per 1M input tokens and $2.64 per 1M output tokens on Azure AI Foundry, with cache reads at $0.13 per 1M tokens. It has a 262,144-token context window and returns up to 262,144 tokens per response.

- Page: https://models.litellm.ai/models/fw-nemotron-3-ultra
- LiteLLM model name: `azure_ai/FW-Nemotron-3-Ultra-NVFP4`
- Context window: 262,144 tokens
- Max output: 262,144 tokens
- Added to LiteLLM: August 14, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Azure AI Foundry (nvfp4) | `azure_ai/FW-Nemotron-3-Ultra-NVFP4` | $0.66 | $2.64 | $0.13 | – | – | 256K |

## Cost examples

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

- Azure AI Foundry: $2.64

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

- Azure AI Foundry: $7.128

## Features

Supported: Function calling, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="azure_ai/FW-Nemotron-3-Ultra-NVFP4",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Fw Nemotron 3 Ultra cost?

Fw Nemotron 3 Ultra costs $0.66 per 1M input tokens and $2.64 per 1M output tokens on Azure AI Foundry, with cache reads at $0.13 per 1M tokens.

### What is the context window of Fw Nemotron 3 Ultra?

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

### Which providers offer Fw Nemotron 3 Ultra?

Fw Nemotron 3 Ultra is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/FW-Nemotron-3-Ultra-NVFP4.

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

Use the LiteLLM Python SDK with model="azure_ai/FW-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 Fw Nemotron 3 Ultra support?

Fw Nemotron 3 Ultra supports function calling, reasoning and prompt caching.

### When did LiteLLM add Fw Nemotron 3 Ultra?

Fw Nemotron 3 Ultra was added to LiteLLM's model price file on August 14, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json