Llama Nemotron Super
Llama Nemotron Super is NVIDIA's language model. A compute-efficient Nemotron Super LLM fine-tuned by NVIDIA on a Llama base, targeting high-accuracy multi-agent and agentic system applications.
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Llama 3.2 11B | — | 128K | $0.160 | $0.160 | |
| Llama 3.2 11B Instruct | — | 128K | $0.350 | $0.350 | |
| Llama 3.2 1B Instruct | — | 128K | $0.027 | $0.080 | |
| Llama 3.2 3B Instruct | — | 131K | $0.015 | $0.020 | |
| Llama 3.2 90B | — | 128K | $0.720 | $0.720 | |
| Llama 3.2 90B Instruct | — | 128K | $2.00 | $2.00 | |
| Llama 3.2 1B | — | 131K | $0.100 | $0.100 | |
| Llama 3.2 3B | — | 131K | $0.040 | $0.080 | |
| Llama 3.1 405B Instruct | — | 131K | $0.120 | $0.300 | |
| Llama 3.1 70B | — | 128K | $0.600 | $0.600 |