Nemotron 3 Ultra

NVIDIA
Nemotron 3 Ultra launch post cover

Cost/1M tokens

input
$0.60
cached
$0.12
output
$2.40
Context
262Ktokens
Released
5mo ago
Size
550Bparameters

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
DeepInfradeepinfra/fp4/flex262K$0.40$1.76$0.08—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-11-12

DeepInfradeepinfra/fp4262K$0.50$2.20$0.10—99.77%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-11-12

KTkt262K$0.50$2.20$0.10—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-11-12

BaseTenbaseten/fp4203K$0.60$2.40$0.12—96.92%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-11-12

BaseTenbaseten/fp4/us203K$0.60$2.40$0.12—97.65%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-11-12

Venicevenice/fp8256K$0.625$3.125$0.1875—99.85%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-11-12

Provider data:OpenRouter

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.