Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Specification
most-agreed values
Context
262K
Max output
128K
Released
2026-06-04
Knowledge cutoff
2025-09
Retires
2026-11-07
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.60
Output
$2.40
Cache read
$0.12
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Priority input | fireworks_ai | $0.75 |
| Priority output | fireworks_ai | $3.00 |
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| fireworks_ai | $0.60 | $2.40 | $0.12 | — | 262K | 33K | 2026-11-07 |
| fireworks-ai · accounts | $0.60 | $2.40 | $0.12 | — | 262K | 128K | — |
| requesty | $0.60 | $2.40 | $0.12 | — | 262K | 262K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | fireworks-ai · accounts | Cache read | $0.119 |
| 2026-09-16 | fireworks-ai · accounts | Cache read | $0.12 |
Other listings of this model
this page is one of them
The corpus files Nemotron 3 Ultra 550B A55B under several keys. This page is the nemotron-3-ultra-nvfp4 listing. The full record — every host, every price and every benchmark score — is on the main Nemotron 3 Ultra 550B A55B page.
More from NVIDIA
most-hosted first