NVIDIAnemotron familyActive

Nemotron 3 Super 120B A12B

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

JSONEmbed chartCompare
Context
256,000
Max output
32,000
Input / 1M
$0.09
Output / 1M
$0.45
Providers
1
01Profile

Profile

Released
2026-03-11
Last updated
2026-03-11
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 1 providers

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

ProviderProvider model idInputOutputCache readContext
pioneernvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8org:nvidia$0.09$0.45$0.09256,000
04History

Change history

12+ recent events since 2026-03-11

2026-08-26Removedwandbofferingremoved→ new
2026-08-19ContextpioneerContext window1,000,000→ 256,000
2026-07-11ContextpioneerMax output16,384→ 32,000
2026-07-02ContextwandbContext window262,144→ new
2026-07-02ContextwandbMax output262,144→ new
2026-06-30ContextpioneerContext window→ 1,000,000
2026-06-30ContextpioneerMax output→ 16,384
2026-06-29ContextpioneerContext window1,000,000→ new
2026-06-29ContextpioneerMax output4,096→ new
2026-06-29Addedpioneeroffering→ new
2026-06-27ContextwandbContext window262,144→ new
2026-06-27ContextwandbContext window→ 262,144
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews