Rank #20
NVIDIA: Nemotron 3 Ultra (free)
- LLM
- 1.0M ctx
- 1M
- $0.00
Model · Vendors
NVIDIA
Ranked models from this vendor or team on Global rankings (same data snapshot as the main global board).
Board snapshot:
About this vendor
NVIDIA publishes Nemotron and other GPU-optimized models for enterprise RAG, reasoning, and edge deployment on aggregator catalogs. Compare Nemotron SKUs on Global Rankings with context, rank, and snapshot OpenRouter pricing.
Vendor snapshot
Catalog models 10
Ranked on Global board 2
Best rank #20
Price range (avg/1M) $0.13–$2.10/1M
Max context 1.0M ctx
Model types
Origins
Top ranked models
Rank #94
NVIDIA: Nemotron 3 Super
- LLM
- 1.0M ctx
- 1M
- $0.24
Models on this board · Global rankings
| Rank | Name | Type | Key metric | 1M tokens (avg) |
|---|---|---|---|---|
| 20 | NVIDIA: Nemotron 3 Ultra (free) | LLM | 1.0M ctx | $0.00 |
| 94 | NVIDIA: Nemotron 3 Super | LLM | 1.0M ctx | $0.24 |
Catalog models (not in ranking)
| Rank | Name | Size | Price | Notes |
|---|---|---|---|---|
| — | NVIDIA: Nemotron 3 Nano 30B A3B | 262k ctx | $0.13/1M | nvidia/nemotron-3-nano-30b-a3b |
| — | NVIDIA: Nemotron 3 Nano 30B A3B (free) | 256k ctx | $0.00/1M | nvidia/nemotron-3-nano-30b-a3b:free |
| — | NVIDIA: Nemotron 3 Nano Omni (free) | 256k ctx | $0.00/1M | nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free |
| — | NVIDIA: Nemotron 3 Super | 1.0M ctx | $0.24/1M | nvidia/nemotron-3-super-120b-a12b |
| — | NVIDIA: Nemotron 3 Super (free) | 262k ctx | $0.00/1M | nvidia/nemotron-3-super-120b-a12b:free |
| — | NVIDIA: Nemotron 3 Ultra | 512k ctx | $2.10/1M | nvidia/nemotron-3-ultra-550b-a55b |
| — | NVIDIA: Nemotron 3 Ultra (free) | 1.0M ctx | $0.00/1M | nvidia/nemotron-3-ultra-550b-a55b:free |
| — | NVIDIA: Nemotron 3.5 Content Safety (free) | 128k ctx | $0.00/1M | nvidia/nemotron-3.5-content-safety:free |
| — | NVIDIA: Nemotron Nano 12B 2 VL (free) | 128k ctx | $0.00/1M | nvidia/nemotron-nano-12b-v2-vl:free |
| — | NVIDIA: Nemotron Nano 9B V2 (free) | 128k ctx | $0.00/1M | nvidia/nemotron-nano-9b-v2:free |
Data sources & methodology
Counts and prices come from the OpenRouter catalog snapshot merged with AI Hippo Global rankings (same snapshot as /rankings/). Rank reflects the composite score on that board—not LMSYS Chatbot Arena ELO. Snapshot date: 2026-08-02. Methodology
FAQ
What is NVIDIA's highest-ranked model?
NVIDIA: Nemotron 3 Ultra (free) currently ranks #20 on AI Hippo's Global rankings board (snapshot 2026-08-02).
What does NVIDIA charge per 1M tokens?
Across catalog and ranked rows, blended 1M-token prices range from $0.13 to $2.10 in the latest snapshot (2026-08-02). Check individual model pages for prompt vs completion splits.
How many NVIDIA models are ranked vs catalog-only?
2 of 10 catalog models appear on Global rankings; the remaining 8 are listed under catalog-only on this page.
Can I compare NVIDIA models?
Yes—use the compare link on this page or open /en/compare/?m=NVIDIA%3A%20Nemotron%203%20Ultra%20(free)&m=NVIDIA%3A%20Nemotron%203%20Super to side-by-side context, price, and composite score for the top ranked models.
How is the Global rankings score calculated?
Global rankings uses on-site weighting (context window first, then blended 1M-token price)—not third-party ELO. Full methodology: /en/methodology/