Nemotron 3 Ultra
language modelNVIDIA
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Key facts
| Made by | NVIDIA |
|---|---|
| Type | language model |
| Released | June 4, 2026 |
| Reads at once | 262,144 tokens |
| Price (API, per million tokens) | $0.6 in · $2.4 out |
| Input → output | text → text |
| Sizes | 550B |
Questions about Nemotron 3 Ultra
Who makes Nemotron 3 Ultra?
Nemotron 3 Ultra is made by NVIDIA.
When was Nemotron 3 Ultra released?
We first saw Nemotron 3 Ultra listed on June 4, 2026.
How much does Nemotron 3 Ultra cost?
Through OpenRouter it costs $0.6 per million input tokens and $2.4 per million output tokens. Prices change, so check the provider before you build on it.
How much text can Nemotron 3 Ultra read at once?
Up to 262,144 tokens, roughly 196.6K words.
More from NVIDIA
NVIDIA-Nemotron-3-NanoNVIDIA · language model
Dec 4, 2025released
NVIDIA-Nemotron-3-UltraNVIDIA · language model
Jun 3, 2026released
NVIDIA-Nemotron-3-SuperNVIDIA · language model
Mar 10, 2026released
NemoClawNVIDIA · developer tool
Mar 15, 2026released
Nemotron-3-Nano-Omni-ReasoningNVIDIA · vision and multimodal model
Apr 20, 2026released
Nemotron 3.5 Super VLNVIDIA · language model
Oct 15, 2026released
Other language models
gpt2Openai Community · language model
Mar 2, 2022released
Qwen3.8Alibaba (Qwen) · language model
Aug 5, 2026released
Qwen3 VLAlibaba (Qwen) · language model
Sep 23, 2025released
Qwen2.5 VLAlibaba (Qwen) · language model
Jan 26, 2025released
optMeta · language model
May 11, 2022released
Qwen3.6Alibaba (Qwen) · language model
Apr 15, 2026released
Ollamaollama · language model
Jun 26, 2023released
pythiaEleutherAI · language model
Feb 8, 2023released
Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with NVIDIA.