modelfax
Models/NVIDIA/Nemotron 3 Ultra 550B A55B
NVIDIAnemotron familyActive

Nemotron 3 Ultra 550B A55B

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

JSONEmbed chartCompare
Context
262,144
Max output
262,144
Input / 1M
$0.60
Output / 1M
$2.40
Providers
2
01 Profile02 Capabilities03 Pricing04 History06 Related
01Profile

Profile

Released
2026-06-04
Last updated
2026-06-13
Knowledge cutoff
—
Weights
Open
02Capabilities

Capabilities

Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing

Pricing across 2 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
fireworks-aiaccounts/fireworks/models/nemotron-3-ultra-nvfp4$0.60$2.40$0.12262,144
requestynemotron-3-ultra-nvfp4$0.60$2.40$0.12262,144
04History

Change history

6+ recent events since 2026-06-04

2026-08-27Price uprequestyinput / 1M$0.54→ $0.60
2026-08-27Price uprequestyoutput / 1M$2.16→ $2.40
2026-08-20Price cutrequestyinput / 1M$0.60→ $0.54
2026-08-20Price cutrequestyoutput / 1M$2.40→ $2.16
2026-08-18Addedrequestyoffering→ new
2026-08-13Addedfireworks-aioffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews