NVIDIA Llama 3.1 Nemotron 70B Instruct is
NVIDIA's language model with a 131K context window and up to 16K output tokens, available from 4 providers, starting at $0.120 / 1M input and $0.300 / 1M output. A 70B-parameter instruction-tuned LLM built on Llama 3.1 and post-trained by NVIDIA with reinforcement learning for precise, helpful responses.
nvidia-llama-3-1-nemotron-70b-instruct |
| Language |
| Active |
| 131K tokens |
| 16K tokens |
| Text |
| Text |
| 70B |
| · 2 years ago |
13.4#212 |
10.8#185 |
11.0#165 |
0.7#158 |
0.5#218 |
0.0#214 |
0.2#207 |
0.2#64 |
0.3#214 |
0.41s#163 |
0.2#205 |
0.7#93 |
0.1#165 |
0.1#198 |
0.0#158 |
0.2#168 |
36.0#174 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities2/13
·
·
✓
✓
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
Lambda | $0.120 | $0.300 |
DeepInfra | $0.600 | $0.600 |
Fireworks AI | $0.900 | $0.900 |
OpenRouter | $1.20 | $1.20 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct | 131K | $0.720 | $0.720 | Available | |
| Llama 3.3 70B Instruct | 131K | $0.100 | $0.300 | Available | |
| Llama 3.3 | — | — | — | — | Available |
| Llama 3.3 70B Instruct Turbo | — | 131K | $0.130 | $0.390 | Available |
| Llama 3.3 70B Versatile | — | 128K | $0.590 | $0.790 | Available |
| Llama 3.3 8B Instruct | — | 128K | — | — | Available |
| Llama 3.2 11B Vision Instruct | 128K | $0.160 | $0.160 | Available | |
| Llama 3.2 1B Instruct | 128K | $0.027 | $0.080 | Deprecated | |
| Llama 3.2 3B Instruct | 131K | $0.015 | $0.020 | Deprecated | |
| Llama 3.2 90B Vision Instruct | 128K | $0.720 | $0.720 | Available | |
| NVIDIA Llama 3.1 Nemotron 70B Instruct | 131K | $0.120 | $0.300 | Current |