Llama-3.1-Nemotron-H-47B
by NVIDIA
· NEMOTRON family · released May 5, 2025
Open weights
Active
Hybrid Mamba-Transformer efficiency.
Pricing
Launch price (from May 5, 2025)
$0.360 in / $0.360 out per 1M tokens
Current price (since May 5, 2025)
$0.360 in / $0.360 out per 1M tokens
Cache read: $0.036/M
| Tier | Effective | In $/M | Out $/M | Cache $/M | Per image | Per second | Source |
|---|---|---|---|---|---|---|---|
| Standard | May 5, 2025 – now | $0.360 | $0.360 | $0.036 | - | - | - |
Specifications
| Model type | Text LLM |
|---|---|
| Architecture | Hybrid |
| Parameters | 47 (7 active) |
| Context window | 131.1K tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | NVIDIA Open Model License |
| Modalities | Text input Text output |
| Tags | Long context |
| End of life | Not disclosed |
| Last verified | Aug 20, 2026 |