# Nemotron 3 Ultra 550B API Pricing

As of October 31, 2026, Nemotron 3 Ultra 550B costs $0.675 per 1M input tokens and $3.375 per 1M output tokens on Kyma API, with cache reads at $0.135 per 1M tokens. It has a 1,000,000-token context window and returns up to 32,768 tokens per response.

- Page: https://models.litellm.ai/models/nemotron-3-ultra-550b
- Lab: NVIDIA
- LiteLLM model name: `kyma/nemotron-3-ultra-550b`
- Context window: 1,000,000 tokens
- Max output: 32,768 tokens
- Added to LiteLLM: October 30, 2026
- Prices updated: October 30, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Kyma API | `kyma/nemotron-3-ultra-550b` | $0.675 | $3.375 | $0.135 | – | – | 1M |

## Cost examples

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

- Kyma API: $3.038

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

- Kyma API: $7.425

## Features

Supported: Function calling, Structured output, Reasoning, Prompt caching.
Not supported: Image input, PDF input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="kyma/nemotron-3-ultra-550b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## Cost calculator

10,000 requests a day with 1,000 input and 500 output tokens each, at Kyma API's price: $0.002363 per request, $23.63 per day, $709 per month (30 days). Try other numbers at https://models.litellm.ai/calculator?model=nemotron-3-ultra-550b

## FAQ

### How much does Nemotron 3 Ultra 550B cost?

Nemotron 3 Ultra 550B costs $0.675 per 1M input tokens and $3.375 per 1M output tokens on Kyma API, with cache reads at $0.135 per 1M tokens.

### What is the context window of Nemotron 3 Ultra 550B?

Nemotron 3 Ultra 550B has a 1,000,000-token context window and returns up to 32,768 tokens per response.

### Which providers offer Nemotron 3 Ultra 550B?

Nemotron 3 Ultra 550B is available from Kyma API through LiteLLM, using the model name kyma/nemotron-3-ultra-550b.

### How do I call Nemotron 3 Ultra 550B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="kyma/nemotron-3-ultra-550b", 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 550B support?

Nemotron 3 Ultra 550B supports function calling, structured output, reasoning and prompt caching. It does not support image input and PDF input.

### When did LiteLLM add Nemotron 3 Ultra 550B?

Nemotron 3 Ultra 550B was added to LiteLLM's model price file on October 30, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change.