# Llama 3.1 Nemotron Ultra 253B

> Llama 3.1 Nemotron Ultra 253B is an open-weight language model from NVIDIA, released on 7 Apr 2025. It accepts text and generates text, with a 128K-token context window and up to 16K output tokens per response.

Source page: https://www.aimodel.directory/models/llama-3-1-nemotron-ultra-253b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** NVIDIA
- **Release date:** 7 Apr 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Max output:** 16K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/llama-3.1-nemotron-ultra-253b-v1.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| NVIDIA NIM | Free | Free | – | 128K |

## FAQ

### What is the context window of Llama 3.1 Nemotron Ultra 253B?

Llama 3.1 Nemotron Ultra 253B has a context window of 128,000 tokens (128K) and can generate up to 16,384 tokens in a single response, according to models.dev.

### Is Llama 3.1 Nemotron Ultra 253B open source?

Llama 3.1 Nemotron Ultra 253B is an open-weight model. Check the license terms before commercial use.

### When was Llama 3.1 Nemotron Ultra 253B released?

NVIDIA released Llama 3.1 Nemotron Ultra 253B on 7 Apr 2025, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Llama 3.1 Nemotron Ultra 253B", https://www.aimodel.directory/models/llama-3-1-nemotron-ultra-253b