# Nvidia Nemotron Super 49B

> Nvidia Nemotron Super 49B is an open-weight language model from NVIDIA, released on 8 Aug 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-3-3-nemotron-super-49b-v1
Last verified: 4 Oct 2026

## Specifications

- **Developer:** NVIDIA
- **Release date:** 8 Aug 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Max output:** 16K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nano-gpt/models/nvidia/Llama-3.3-Nemotron-Super-49B-v1.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of Nvidia Nemotron Super 49B?

Nvidia Nemotron Super 49B 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 Nvidia Nemotron Super 49B open source?

Nvidia Nemotron Super 49B is an open-weight model. Check the license terms before commercial use.

### When was Nvidia Nemotron Super 49B released?

NVIDIA released Nvidia Nemotron Super 49B on 8 Aug 2025, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Nvidia Nemotron Super 49B", https://www.aimodel.directory/models/llama-3-3-nemotron-super-49b-v1