NVIDIA
Nemotron 3 Ultra
Launched 2026-06-04 · Knowledge up to 2025-09 · Listed on OpenRouter 2026-06-04
Prices updated . Benchmarks updated .
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...
You send / 1M
$0.500
tokens in
It replies / 1M
$2.20
tokens out
Context
1.05M
tokens it can read at once
Typical request
$0.0018
1,000 words in, 400 out
Benchmarks
| Benchmark | Score | Kind | Date | Source |
|---|---|---|---|---|
| Epoch Capabilities Index | 146.0 | Independent | 2026-06-04 | Epoch AI |
| GPQA Diamond | 85.3% | Independent | 2026-08-10 | Epoch AI |
| OTIS Mock AIME | 86.7% | Independent | 2026-08-10 | Epoch AI |
| CritPt | 3.1% | Independent | 2026-06-04 | CritPt, republished by Epoch AI |
Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp4 | $0.400 | $1.76 | 98% | Read |
| DeepInfra · fp4 | $0.500 | $2.20 | 100% | Read |
| BaseTen · fp4 | $0.600 | $2.40 | 100% | Read |
| Venice · fp8 | $0.625 | $3.13 | 97% | Read |
| DeepInfra · fp4 | $0.750 | $3.30 | 97% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Weights: Open weights
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 66K tokens
- Repeated text is billed at $0.100 per 1M (prompt caching)
Compare with
Appears in
Estimate your monthly cost with Nemotron 3 Ultra
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.
