Nemotron 3 Ultra NVFP4
NVIDIAnemotron-3-ultra-nvfp4
Released Jun 4, 2026
Providers
3
Context
1.0M
Input
$0.50/M
Output
$2.20/M
Aliases:nemotron-3-ultranvidia-nemotron-3-ultra-nvfp4
NVIDIA's frontier-scale hybrid Latent-MoE model (550B total, 55B active) for the most demanding agentic, reasoning, and long-context workloads across code, math, and science. Trained with an NVFP4 recipe.
NVIDIA's frontier-scale hybrid Latent-MoE model (550B total, 55B active) for the most demanding agentic, reasoning, and long-context workloads across code, math, and science. Trained with an NVFP4 recipe.
DeepInfra
deepinfra/nemotron-3-ultra-nvfp4
262K context16K max outQuant: fp4
Input Price
$0.50/M tokens
Output Price
$2.20/M tokens
Cache read: $0.10/M
Fireworks AI
fireworks/nemotron-3-ultra-nvfp4
262K context66K max outQuant: Unspecified
Flex
Input Price
$0.60/M tokens
Output Price
$2.40/M tokens
Cache read: $0.12/M
Nebius
nebius/nemotron-3-ultra-nvfp4
1.0M context66K max outQuant: fp4
FlexPriority / Fast
Input Price
$1.00/M tokens
Output Price
$3.00/M tokens