HASTATAgent stack guide nemotron
NVIDIA Nemotron 3 Ultra
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context256K
Output256K
Providers3
CapabilitiesTool calling, Reasoning
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Basetennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.60 | $2.40 | $0.12 | 198K | 2026-06-04 |
 Venice AInvidia-nemotron-3-ultra-550b-a55b | $0.63 | $3.13 | $0.19 | 256K | 2026-06-11 |
 Weights & Biasesnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.75 | $2.75 | $0.15 | 256K | 2026-06-04 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text → text