HASTATAgent stack guide nemotron
Nvidia Nemotron 3 Ultra 550B Thinking
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 context1M
Output64K
Providers1
CapabilitiesTool calling, Reasoning
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 NanoGPTnvidia/nemotron-3-ultra-550b-a55b:thinking | $0.50 | $2.50 | $0.25 | 1M | 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