NVIDIA: Nemotron 3 Ultra (free)nvidia
NVIDIA: Nemotron 3 Ultra (free): Free/1M input, Free/1M output, 1.0M 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 | Free |
| Output | Free |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.00 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 66K |
| 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 (free) API cost?
NVIDIA: Nemotron 3 Ultra (free) costs Free/1M input tokens and Free/1M output tokens. Blended cost at a 3:1 ratio is about $0.00/1M tokens.
What is the context window of NVIDIA: Nemotron 3 Ultra (free)?
NVIDIA: Nemotron 3 Ultra (free) supports a 1.0M token context window with up to 66K output tokens.
Is NVIDIA: Nemotron 3 Ultra (free) worth it?
NVIDIA: Nemotron 3 Ultra (free) has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.