MODEL PROOF
Nemotron 3 Ultra
NOT INDEPENDENTLY RATED
No independent LMArena score is published for this model.
Serving precision differs between offers.
- 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 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) |
|---|---|---|---|---|
| DeepInfradeepinfra/fp4 Endpoint terms
| $0.500 | $2.20 | fp4 | 99.95% |
| BaseTenbaseten/fp4 Endpoint terms
| $0.600 | $2.40 | fp4 | 99.97% |
| BaseTenbaseten/fp4 Endpoint terms
| $0.600 | $2.40 | fp4 | 99.98% |
| Venicevenice/fp8 Endpoint terms
| $0.625 | $3.13 | fp8 | 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, 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 |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | unrated |
| Cross-checked | vendor page |
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