Nemotron 3 Ultra
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...
What published route metadata supports
Only source-backed fields are filled
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterFree | nvidia/nemotron-3-ultra-550b-a55b:free | $0 | — | $0 | 1M | OpenRouter API ↗ |
| OpenRouterStandard | nvidia/nemotron-3-ultra-550b-a55b | $0.6 | $0.12 | $2.4 | 262K | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
6 verified price changes since Aug 26, 2026
1 route availability change recorded. No earlier prices are inferred.
- Sep 19, 2026OpenRouter · Standard
Input $0.625 → $0.6 · Cached input $0.1875 → $0.12 · Output $3.12 → $2.4
- Sep 17, 2026OpenRouter · Standard
Input $0.6 → $0.625 · Cached input $0.12 → $0.1875 · Output $2.4 → $3.12
- Sep 14, 2026OpenRouter · Standard
Input $0.625 → $0.6 · Cached input $0.1875 → $0.12 · Output $3.12 → $2.4
- Sep 4, 2026OpenRouter · Standard
Input $0.6 → $0.625 · Cached input $0.12 → $0.1875 · Output $2.4 → $3.12
- Sep 3, 2026OpenRouter · Batch
Pricing route removed
- Sep 3, 2026OpenRouter · Standard
Input $0.5 → $0.6 · Cached input $0.1 → $0.12 · Output $2.2 → $2.4