AGENTKERNEL
- Home
- All models
- Nemotron 3 Ultra
Nemotron 3 Ultra: price, performance and context
Open Nemotron 3 Ultra by NVIDIA costs $0.50 per 1M input and $2.20 per 1M output tokens, handles up to 262.1K tokens in one request (≈ 790 pages of text) and scores 22.9 points on the AgentKernel performance index, rank 79 of 212.
Privacy: zero data retention with 3 providers, not in the EU. Availability over the last 24 h: 100%.
Open in the interactive comparisonKey facts
- Licence
- Open weights: free to download and self-host
- Input / 1M tokens
- $0.50
- Output / 1M tokens
- $2.20
- Context window
- 262.1K tokens
- Max. output
- 16.4K tokens
- Performance index
- 22.9 points · rank 79 of 212
- Coding index
- 49.3 points · rank 59 of 119
- Agentic index
- 20.1 points · rank 43 of 91
- Cost at your usage
- $1.05 / month
- Knowledge cutoff
- n/a
- In the catalog since
- Jun 04, 2026
- Capabilities
- Reasoning, Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|---|---|
| Chat repliesA question with a short history, a detailed answer | $0.001 | 8,000 |
| Email draftsBullet points in, a finished email out | $0.001 | 10,000 |
| Document summariesRead 10 pages, write a one-page summary | $0.003 | 3,600 |
| Code reviewsReview and comment on 500 lines of code | $0.005 | 2,000 |
| Book analysesAnalyse a 300-page book in one go | $0.054 | 180 |
Cheaper with similar performance
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |
| Ling 3.0 Flash VLinclusionAI | Open | 24.6 | $0.036 |
| Ling 3.0 FlashinclusionAI | Open | 20.1 | $0.037 |
Stronger models
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| GPT-5OpenAI | Proprietary | 23 | $3.75 |
| GLM 5V TurboZ.ai | Proprietary | 23.5 | $2.20 |
| Kimi K2.5Moonshot AI | Open | 23.5 | $1.013 |