Llama 3.1 Nemotron 1 Ultra 253B Reasoning
Llama 3.1 Nemotron 1 Ultra 253B Reasoning is an AI model from NVIDIA. A 253B-parameter reasoning-specialized variant of NVIDIA's Nemotron Ultra, built on Llama 3.1 for complex multi-step inference and agentic workflows.
NVIDIA. A 253B-parameter reasoning-specialized variant of NVIDIA's Nemotron Ultra, built on Llama 3.1 for complex multi-step inference and agentic workflows.nvidia-llama-3-1-nemotron-1-ultra-253b-reasoning |
| Active |
| NVIDIA |
15.0#282 |
13.1#250 |
63.7#102 |
0.8#61 |
0.7#151 |
0.1#163 |
0.6#94 |
0.7#27 |
0.4#231 |
0.70s#278 |
0.3#169 |
1.0#34 |
0.6#102 |
0.1#289 |
0.0#289 |
0.1#334 |
41.1#226 |
Capabilities
Input0/5
·
·
·
·
·
Output0/5
·
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Llama 3.1 Nemotron 1 Ultra 253B Reasoning | — | — | — | — | Current |
| Llama 3.1 Nemotron 1 Ultra 253B | — | 128K | $0.600 | $1.80 | Available |
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 70B | — | 128K | $0.600 | $0.600 | |
| Llama 3.1 70B Instruct | — | 131K | $0.100 | $0.100 |