NVIDIA Llama 3.1 Nemotron 1 Ultra 253B
NVIDIA Llama 3.1 Nemotron 1 Ultra 253B is NVIDIA's language model with a 128K context window, starting at $0.600 / 1M input and $1.80 / 1M output. A 253B-parameter ultra-scale LLM fine-tuned by NVIDIA on Llama 3.1, targeting high-accuracy reasoning and complex instruction-following tasks.
NVIDIA's language model with a 128K context window, starting at $0.600 / 1M input and $1.80 / 1M output. A 253B-parameter ultra-scale LLM fine-tuned by NVIDIA on Llama 3.1, targeting high-accuracy reasoning and complex instruction-following tasks.15.0#184 |
13.1#162 |
63.7#58 |
0.8#37 |
0.7#86 |
0.1#92 |
0.6#60 |
0.7#15 |
0.4#144 |
0.73s#217 |
0.3#103 |
1.0#20 |
0.6#58 |
0.1#195 |
0.0#191 |
0.1#232 |
42.4#165 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities1/13
·
·
✓
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Nebius | $0.600 | $1.80 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct | — | 131K | $0.720 | $0.720 | |
| Llama 3.3 70B Instruct | — | 131K | $0.100 | $0.300 | |
| Llama 3.3 | — | — | — | — | — |
| Llama 3.3 70B Instruct Turbo | — | — | 131K | $0.130 | $0.390 |
| Llama 3.3 70B Versatile | — | — | 128K | $0.590 | $0.790 |
| Llama 3.3 8B Instruct | — | — | 128K | — | — |
| Llama 3.2 11B Vision Instruct | — | 128K | $0.160 | $0.160 | |
| Llama 3.2 1B Instruct | — | 128K | $0.027 | $0.080 | |
| Llama 3.2 3B Instruct | — | 131K | $0.015 | $0.020 | |
| Llama 3.2 90B Vision Instruct | — | 128K | $0.720 | $0.720 |