Nemotron-4 340B
by NVIDIA
· NEMOTRON family · released Jun 14, 2024
Open weights
Active
Largest open synthetic-data generation model.
Pricing
Launch price (from Jun 14, 2024)
- in / - out per 1M tokens
Current price (since Jun 14, 2024)
- in / - out per 1M tokens
| Tier | Effective | In $/M | Out $/M | Cache $/M | Per image | Per second | Source |
|---|---|---|---|---|---|---|---|
| Standard | Jun 14, 2024 – now | - | - | - | - | - | - |
Specifications
| Model type | Text LLM |
|---|---|
| Architecture | Dense |
| Parameters | 340 |
| Context window | 4.1K tokens |
| Max output | Not disclosed tokens |
| Knowledge cutoff | Not disclosed |
| License | NVIDIA Open Model License |
| Modalities | Text input Text output |
| Tags | Flagship |
| End of life | Not disclosed |
| Last verified | Aug 20, 2026 |
Benchmarks
| Benchmark | Score | Src |
|---|---|---|
| MMLU | 81.1% | official |