--- title: "NVIDIA: Nemotron 3 Ultra — unrated, priced in this catalogue · Undominated.ai" canonical: https://undominated.ai/models/nvidia__nemotron-3-ultra-550b-a55b/ description: "NVIDIA: Nemotron 3 Ultra: $0.625/M in, $3.13/M out. No independent quality score in this catalogue — unrated, not ranked, not scored zero." --- # NVIDIA: Nemotron 3 Ultra — unrated, priced in this catalogue · Undominated.ai > NVIDIA: Nemotron 3 Ultra: $0.625/M in, $3.13/M out. No independent quality score in this catalogue — unrated, not ranked, not scored zero. [Check base rates for this workload](/check/nvidia__nemotron-3-ultra-550b-a55b/) [Cheaper alternatives](/alternatives/) [Family](/families/nemotron/) [Compare models](https://undominated.ai/compare/?models=nvidia%2Fnemotron-3-ultra-550b-a55b) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # Nemotron 3 Ultra NVIDIA · 04 Jun 2026 · openmdw-1.1 Balanced Summarise Chat Code gen Agentic NOT INDEPENDENTLY RATED ## No independent LMArena score is published for this model. **$1.25** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [Vendor cross-check](https://openrouter.ai/api/v1/models) Independent LMArena score Not independently rated Context window 262.14K Maximum output 16.38K Input modalities text Output modalities text Published input price $0.625 / 1M tokens Published output price $3.13 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from Venice: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known. Cheaper right now: $0.925/M at DeepInfra — 4-bit It does not pass the like-for-like test, so it never sets a rank. Every price dimension · USD per million tokens | Input | $0.625 /M | | --- | --- | | Output | $3.13 /M | | Cached input | $0.188 /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.625/M from Venice. 4 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller DeepInfra deepinfra/fp4 Endpoint terms Cached input /M $0.100 Context limit 262,144 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.500 | Output $2.20 | Precision fp4 | Uptime (1d) 99.95% | | Seller BaseTen baseten/fp4 Endpoint terms Cached input /M $0.120 Context limit 202,800 tokens Output limit 182,520 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.600 | Output $2.40 | Precision fp4 | Uptime (1d) 99.97% | | Seller BaseTen baseten/fp4 Endpoint terms Cached input /M $0.120 Context limit 202,800 tokens Output limit 182,520 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes Unknown | Input $0.600 | Output $2.40 | Precision fp4 | Uptime (1d) 99.98% | | Seller Venice venice/fp8 Endpoint terms Cached input /M $0.188 Context limit 256,000 tokens Output limit 32,768 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.625 | Output $3.13 | Precision fp8 | Uptime (1d) 96.96% | ### Independent scores No independent benchmark has measured this model. Unrated is not a score of zero. #### Best rankings by task - ASCII art #59 1105 - 3D #66 1140 - Game development #68 1152 - SVG #68 1068 - UI components #75 1146 - Code categories #77 1149 - Data visualisation #77 1147 - Websites #85 1146 Per-task Elo and rank from [Design Arena](https://designarena.ai), via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list. ### Capability | Context window | 262K | | --- | --- | | Max output | 16K | | Input modes | text | | Tool use | yes | | Reasoning | optional | | Open weights | yes | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | unrated | | Cross-checked | [vendor page](https://openrouter.ai/api/v1/models) | People search Nemotron 3 Ultra vs without naming an opponent. This page will not invent one. Ultra is unrated here. Unrated is not a score of zero. 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... ## Questions this page answers What does Nemotron 3 Ultra cost? $0.625/M in, $3.13/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Nemotron 3 Ultra have an independent quality score? Nemotron 3 Ultra has no independent quality score in this catalogue. Unrated is not a score of zero. What beats Nemotron 3 Ultra? Nemotron 3 Ultra has no independent quality score. Unrated is not a score of zero. Does this page use Artificial Analysis scores for Nemotron 3 Ultra? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Does a missing score mean Nemotron 3 Ultra scored zero? Unrated is not a score of zero. Is the cheapest Nemotron 3 Ultra endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.625/M from Venice. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options NVIDIA: Nemotron 3 Ultra. Balanced workload. Not independently rated. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related No independent quality score, so there is no dominator to name. Unrated is not a clean bill of health. - Same vendor [Nemotron 3 Nano 30B A3B](/models/nvidia__nemotron-3-nano-30b-a3b/) - NVIDIA models [NVIDIA](/providers/nvidia/) - Where this model appears [wire](/wire/) - Same vendor [Nemotron 3 Super](/models/nvidia__nemotron-3-super-120b-a12b/) - Where this model appears [self-host](/self-host/) - Same vendor [Nemotron 3.5 Content Safety](/models/nvidia__nemotron-3.5-content-safety/) - Where this model appears [spreads](/spreads/) - Where this model appears [traps](/traps/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![Nemotron 3 Ultra — Undominated.ai dominance verdict](https://undominated.ai/badge/nvidia__nemotron-3-ultra-550b-a55b.svg)](https://undominated.ai/models/nvidia__nemotron-3-ultra-550b-a55b/) HTML Copy Nemotron 3 Ultra — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/nvidia__nemotron-3-ultra-550b-a55b.svg](https://undominated.ai/badge/nvidia__nemotron-3-ultra-550b-a55b.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)