Nemotron 3 Ultra 550B A55B
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...
Cheapest input
$0.5
$/MTok · models.dev
Cheapest output
$2.20
$/MTok
Context
1M
tokens
Offers
5
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 offers.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestnvidia/nemotron-3-ultra-550b-a55b | Kilo Gateway | $0.5 | $2.20 | $0.1 | 512K |
| models.devnvidia/nemotron-3-ultra-550b-a55b | NVIDIA | $0.5 | $2.50 | $0.15 | 1M |
| models.devnvidia/nemotron-3-ultra-550b-a55b | Vercel AI Gateway | $0.6 | $2.40 | $0.12 | 1M |
| OpenRouternvidia/nemotron-3-ultra-550b-a55b | OpenRouter | $0.6 | $3.60 | $0.2 | 512K |
| models.devnvidia/nemotron-3-ultra-550b-a55b | Together AI | $0.6 | $3.60 | $0.2 | 512K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Released: 2026-06-04Family: nemotron
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence37.8
- AA coding49.3
- AA agentic27.4
Sources: Arena AI, Artificial Analysis. See /benchmarks.