NVIDIAnemotron familyActive

Nemotron 3 Ultra 550B A55B

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

JSONEmbed chartCompare
Context
1,048,576
Max output
1,048,576
Input / 1M
$0.50
Output / 1M
$2.15
Providers
15
01Profile

Profile

Released
2026-06-04
Last updated
2026-06-11
Knowledge cutoff
Weights
Open
02Capabilities

Capabilities

Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
$0.15
Cache write
Not listed
03Pricing

Pricing across 13 providers

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

ProviderProvider model idInputOutputCache readContext
nvidiafirst-partynvidia/nemotron-3-ultra-550b-a55b$0.50$2.50$0.151,000,000
edenaideepinfra/nemotron-3-ultra-550b-a55b$0.50$2.20$0.10262,144
kilonvidia/nemotron-3-ultra-550b-a55b$0.50$2.20$0.10256,000
nano-gptnvidia/nemotron-3-ultra-550b-a55b$0.50$2.50$0.251,000,000
nano-gptnvidia/nemotron-3-ultra-550b-a55b:thinkingthinking$0.50$2.50$0.251,000,000
wandbnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Borg:nvidia$0.50$2.15$0.10262,144
basetennvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Borg:nvidia$0.60$2.40$0.12202,800
togetherainvidia/nemotron-3-ultra-550b-a55b$0.60$3.60$0.20512,300
vercelnvidia/nemotron-3-ultra-550b-a55b$0.60$2.40$0.121,000,000
openrouternvidia/nemotron-3-ultra-550b-a55b$0.63$3.13$0.19262,144
venicenvidia-nemotron-3-ultra-550b-a55borg:nvidia$0.63$3.13$0.19256,000
edenainebius/nvidia/Nemotron-3-Ultra-550b-a55b$1.00$3.00$1.001,048,576
Show all 19 providers ↓
ProviderProvider model idInputOutputCache readContext
nebiusnvidia/Nemotron-3-Ultra-550b-a55b$1.00$3.00$1.001,048,576
bothubnemotron-3-ultra-550b-a55b:freefreeFreeFreeFree1,000,000
kenarinemotron-3-ultra-550b-a55bNot listedNot listedNot listed1,000,000
kilonvidia/nemotron-3-ultra-550b-a55b:freefreeFreeFreeFree1,000,000
openrouternvidia/nemotron-3-ultra-550b-a55b:freefreeFreeFreeFree1,000,000
requestynemotron-3-ultra-550b-a55bNot listedNot listedNot listed1,048,576
unorouternemotron-3-ultra-550b-a55b:freefreeFreeFreeFree1,000,000
04History

Change history

12+ recent events since 2026-06-04

2026-09-16ContextkiloContext window202,800→ 256,000
2026-09-16ContextkiloMax output182,520→ 32,768
2026-09-16Price upopenrouterinput / 1M$0.60→ $0.63
2026-09-16Price upopenrouteroutput / 1M$2.40→ $3.13
2026-09-16ContextopenrouterMax output182,520→ 32,768
2026-09-14ContextkiloContext window256,000→ 202,800
2026-09-14ContextkiloMax output32,768→ 182,520
2026-09-14Price cutopenrouterinput / 1M$0.63→ $0.60
2026-09-14Price cutopenrouteroutput / 1M$3.13→ $2.40
2026-09-14ContextopenrouterMax output32,768→ 182,520
2026-09-14Price cutwandbinput / 1M$0.75→ $0.50
2026-09-14Price cutwandboutput / 1M$2.75→ $2.15
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews