prices synced 2026-10-27
N

Nemotron 3 Ultra

NVIDIA · Released Jun 2026

Compare

A 55-billion-parameter mixture-of-experts model from NVIDIA with a hybrid Transformer-Mamba architecture and 512K token context window.

Strengths
Handles extended context and complex reasoning tasks with a large context window and hybrid architecture designed for both token prediction and state-space efficiency.
Best for
Long-context reasoning, document analysis, and task orchestration workflows that benefit from the expanded context window.
Limitations
Larger than Lightning and earlier Nano models; not the newest release in the Nemotron lineup, having been superseded by Nemotron 3.5 Lightning in 2026.

Input / 1M

$0.6

Output / 1M

$2.40

Cached input / 1M

$0.12

Context window

202K

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $2.50 to $2.40; Input went from $0.5 to $0.6 between Jun 2026 and Oct 2026.$0$1.00$2.00$3.00$4.00Output on 11 Jun 2026: $2.50Output on 17 Jun 2026: $2.20Output on 15 Jul 2026: $3.60Output on 23 Jul 2026: $2.20Output on 25 Jul 2026: $3.60Output on 27 Jul 2026: $2.20Output on 28 Jul 2026: $2.20Output on 30 Jul 2026: $3.60Output on 1 Aug 2026: $3.60Output on 28 Aug 2026: $2.20Output on 2 Sep 2026: $3.12Output on 3 Sep 2026: $2.40Output on 4 Sep 2026: $3.12Output on 14 Sep 2026: $2.40Output on 16 Sep 2026: $3.12Output on 19 Sep 2026: $2.40Output on 2 Oct 2026: $2.40Output on 3 Oct 2026: $2.20Output on 11 Oct 2026: $2.40Out $2.40Input on 11 Jun 2026: $0.5Input on 17 Jun 2026: $0.5Input on 15 Jul 2026: $0.6Input on 23 Jul 2026: $0.5Input on 25 Jul 2026: $0.6Input on 27 Jul 2026: $0.5Input on 28 Jul 2026: $0.5Input on 30 Jul 2026: $0.6Input on 1 Aug 2026: $0.6Input on 28 Aug 2026: $0.5Input on 2 Sep 2026: $0.625Input on 3 Sep 2026: $0.6Input on 4 Sep 2026: $0.625Input on 14 Sep 2026: $0.6Input on 16 Sep 2026: $0.625Input on 19 Sep 2026: $0.6Input on 2 Oct 2026: $0.6Input on 3 Oct 2026: $0.5Input on 11 Oct 2026: $0.6In $0.6Jun 2026Oct 2026

Price change

30d
in decreased 0.0% out decreased 0.0%
90d
in increased 20.0% out increased 9.1%
1y
in increased 20.0% out decreased 4.0%
Since launch
in increased 20.0% out decreased 4.0%

Snapshots

Effective Input Output Cached in Note Source
11 Oct 2026 $0.6 $2.40 $0.12 Imported from OpenRouter openrouter.ai
3 Oct 2026 $0.5 $2.20 $0.1 Imported from OpenRouter openrouter.ai
2 Oct 2026 $0.6 $2.40 $0.12 Imported from OpenRouter openrouter.ai
19 Sep 2026 $0.6 $2.40 $0.12 Imported from OpenRouter openrouter.ai
16 Sep 2026 $0.625 $3.12 $0.1875 Imported from OpenRouter openrouter.ai
14 Sep 2026 $0.6 $2.40 $0.12 Imported from OpenRouter openrouter.ai
4 Sep 2026 $0.625 $3.12 $0.1875 Imported from OpenRouter openrouter.ai
3 Sep 2026 $0.6 $2.40 $0.12 Imported from OpenRouter openrouter.ai
2 Sep 2026 $0.625 $3.12 $0.1875 Imported from OpenRouter openrouter.ai
28 Aug 2026 $0.5 $2.20 $0.1 Imported from OpenRouter openrouter.ai
1 Aug 2026 $0.6 $3.60 $0.2 Imported from OpenRouter openrouter.ai
30 Jul 2026 $0.6 $3.60 $0.2 Imported from OpenRouter openrouter.ai
28 Jul 2026 $0.5 $2.20 $0.1 Imported from OpenRouter openrouter.ai
27 Jul 2026 $0.5 $2.20 $0.1 Imported from OpenRouter openrouter.ai
25 Jul 2026 $0.6 $3.60 $0.2 Imported from OpenRouter openrouter.ai
23 Jul 2026 $0.5 $2.20 $0.1 Imported from OpenRouter openrouter.ai
15 Jul 2026 $0.6 $3.60 $0.2 Imported from OpenRouter openrouter.ai
17 Jun 2026 $0.5 $2.20 $0.1 Imported from OpenRouter openrouter.ai
11 Jun 2026 $0.5 $2.50 $0.15 Imported from OpenRouter openrouter.ai

More from NVIDIA

Report a problem