Llama-3.1-Nemotron-Nano-9B-v2
by NVIDIA
· NEMOTRON family · released Aug 6, 2025
Open weights
Active
Device-scale multimodal hybrid.
Pricing
Launch price (from Aug 6, 2025)
$0.080 in / $0.080 out per 1M tokens
Current price (since Aug 6, 2025)
$0.080 in / $0.080 out per 1M tokens
Cache read: $0.0080/M
| Tier | Effective | In $/M | Out $/M | Cache $/M | Per image | Per second | Source |
|---|---|---|---|---|---|---|---|
| Standard | Aug 6, 2025 – now | $0.080 | $0.080 | $0.0080 | - | - | - |
Specifications
| Model type | Multimodal |
|---|---|
| Architecture | Hybrid |
| Parameters | 9 |
| Context window | 131.1K tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Jun 1, 2025 |
| License | NVIDIA Open Model License |
| Modalities | Text input Image input Text output |
| Tags | Small LM Vision |
| End of life | Not disclosed |
| Last verified | Aug 20, 2026 |