What is the context window of Nemotron 3 Ultra (free)?

1M tokens, with up to 66K output tokens per response.

Does Nemotron 3 Ultra (free) support images, tools and structured output?

Images as input: no. Tool calling: yes. Structured (JSON) output: no. Reasoning mode: yes.

NVIDIA

Free model by NVIDIA · 1M context · tools, reasoning, open weights, free.

Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026

input / 1M tokens

output / 1M tokens

context window

66K

max output

22.9

Artificial Analysis intelligence index

We started tracking Nemotron 3 Ultra (free) on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.

Model ID	`nvidia/nemotron-3-ultra-550b-a55b:free`
Input	text
Output	text
Tool calling	Yes
Structured output	No
Reasoning mode	Yes
Open weights	Yes — nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Released	Jun 4, 2026

What is the context window of Nemotron 3 Ultra (free)?: 1M tokens, with up to 66K output tokens per response.
Does Nemotron 3 Ultra (free) support images, tools and structured output?: Images as input: no. Tool calling: yes. Structured (JSON) output: no. Reasoning mode: yes.