NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning)
No published training cutoff
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
Price not published
NVIDIA Nemotron 3 Ultra (550B-A55B)
NVIDIA’s largest open reasoning model for agentic workflows and long-context analysis.
Model idnvidia/nemotron-3-ultra-550b-a55b
Price$0.60 in, $2.40 out per 1M tokens
Checked29 September 2026
Knows up to September 2025
1,990events after its cutoff
86 historic, 455 major. 409 days of news.
It launched on 4 June 2026, already missing 168 of them. Coverage before 2026 is thin (80 entries for 2025), so this count is a floor.
Five things it has never heard of
Its cutoff, September 2025, is before this chart starts: every mark here is news it has never seen.
How to call it
3 ways to use NVIDIA Nemotron 3 Ultra (550B-A55B), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| NVIDIA API (build.nvidia.com) | nvidia/nemotron-3-ultra-550b-a55b |
https://integrate.api.nvidia.com/v1/chat/completions |
build.nvidia.com |
| OpenRouter | nvidia/nemotron-3-ultra-550b-a55b |
openrouter.ai | |
| Hugging Face | huggingface.co |
Pricing
| Input | $0.60 per 1M tokens |
|---|---|
| Output | $2.40 per 1M tokens |
As published: “per 1M tokens (USD) on OpenRouter (262K context there); NVIDIA hosted pricing not verified”.
Source: openrouter.ai, checked 29 September 2026.
Specs
- Input
- Text
- Output
- Text
- Context window
- 1,000,000 tokens
- Max output
- Not published
- Open weights
- Yes
- Licence
- OpenMDW-1.1
- Training cutoff
- September 2025
- Released
- 4 June 2026
- Status
- Current
- Type
- Reasoning model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Hybrid Mamba-2 / LatentMoE at frontier scale
550B total / 55B active; interleaved Mamba-2 and LatentMoE layers with select attention, plus multi-token prediction for faster generation.
NVFP4 pretraining and weights
Pre-trained with an NVFP4 recipe; weights published in both BF16 and NVFP4 under the permissive OpenMDW-1.1 license.
Reasoning on / off / medium
enable_thinking toggle in the chat template plus a medium-effort mode to cut reasoning tokens.
Four assistants, one scale
NVIDIA Nemotron 3 Ultra (550B-A55B) is added as a fifth row. Each row runs from what the model knows (graphite) through the months between its cutoff and its launch (hatched) to today (pink).
- GPT-6 Astra 271 at launch, 1,863 today
- Claude Opus 5.5 372 at launch, 1,795 today
- Gemini 4 Hydrogen 1,863 at launch, 1,889 today
- Grok 4.7 387 at launch, 1,829 today
- NVIDIA Nemotron 3 Ultra (550B-A55B) 168 at launch, 1,990 today
Show as a table
| Model | Cutoff | Released | Missing at launch | Missing today |
|---|---|---|---|---|
| GPT-6 Astra | April 2026 | 3 September 2026 | 271 | 1,863 |
| Claude Opus 5.5 | June 2026 | 22 September 2026 | 372 | 1,795 |
| Gemini 4 Hydrogen | March 2026 | 12 November 2026 | 1,863 | 1,889 |
| Grok 4.7 | May 2026 | 21 September 2026 | 387 | 1,829 |
| NVIDIA Nemotron 3 Ultra (550B-A55B) | September 2025 | 4 June 2026 | 168 | 1,990 |
Notes
Knowledge cutoff = pre-training data (Sep 2025); post-training data to May 2026. NVFP4 repo nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4.
curl https://integrate.api.nvidia.com/v1/chat/completions -H "Authorization: Bearer $NVIDIA_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"Hello"}]}'
Sources: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 , https://integrate.api.nvidia.com/v1/models