NVIDIA: Nemotron 3 Ultranvidia
Bottom Line
NVIDIA: Nemotron 3 Ultra: $0.60/1M input, $2.40/1M output, 262K context. 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...
API Pricing (per 1M tokens)
| Input | $0.60 |
| Output | $2.40 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $1.05 |
Specs & Performance
| Context Length | 262K |
| Max Output | 183K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from nvidia
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the NVIDIA: Nemotron 3 Ultra API cost?
NVIDIA: Nemotron 3 Ultra costs $0.60/1M input tokens and $2.40/1M output tokens. Blended cost at a 3:1 ratio is about $1.05/1M tokens.
What is the context window of NVIDIA: Nemotron 3 Ultra?
NVIDIA: Nemotron 3 Ultra supports a 262K token context window with up to 183K output tokens.
Is NVIDIA: Nemotron 3 Ultra worth it?
NVIDIA: Nemotron 3 Ultra has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.