NVIDIA: Nemotron 3 Ultra (free)
NVIDIA: Nemotron 3 Ultra (free) ranks #48 of 94 models by Artificial Analysis quality score (22.9) at $1.05/1M tokens blended - and ranks #10 of 353 by average real OpenRouter usage share over the trailing 80-day window (3.90%). Available from 4 providers at up to 100.0% uptime.
- Quality (Intelligence Index) - 22.9
- Coding index - 49.3
- Agentic index - 20.1
- Price (blended $/1M) - 1.05
- Context window - 262,144
- Usage rank - #10 of 353
- Providers - 4
- Open/closed - open
Usage share over time
What NVIDIA: Nemotron 3 Ultra (free) is actually used for
Share of each real task category's classified traffic this model handles, from OpenRouter's task classification.
| Task | Share of task traffic |
|---|---|
| Frontend & UI | 4.7% |
| DevOps | 4.5% |
| Repo Scanning | 4.4% |
| DevOps & Config | 4.3% |
| Debugging | 3.5% |
| SQL & Database | 2.9% |
| Shell Execution | 2.8% |
| Code Generation | 2.5% |
Compare NVIDIA: Nemotron 3 Ultra (free)
Frequently asked questions
What is NVIDIA: Nemotron 3 Ultra (free)'s quality score?
NVIDIA: Nemotron 3 Ultra (free) scores 22.9 on Artificial Analysis's Intelligence Index, ranking #48 of 94 models with a published score.
How much does NVIDIA: Nemotron 3 Ultra (free) cost?
NVIDIA: Nemotron 3 Ultra (free) costs $1.05 per 1M tokens (blended 75% prompt / 25% completion pricing).
Is NVIDIA: Nemotron 3 Ultra (free) widely used?
NVIDIA: Nemotron 3 Ultra (free) ranks #10 of 353 models by average real OpenRouter usage share, averaging 3.90% of classified token volume over the trailing 80-day window.
Is NVIDIA: Nemotron 3 Ultra (free) open-weight or closed?
NVIDIA: Nemotron 3 Ultra (free) is an open-weight model.
Source: OpenRouter (openrouter.ai/rankings), as of September 23, 2026.
Benchmark scores: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings).
Methodology: www.smophy.ai/benchmark/methodology
Token counts originate from each provider's own tokenizer and are not directly comparable across providers.