| usdvalidate | nvidia | 0 | |
| Active Speaker Detection | nvidia | 0 | |
| Llama 3.1 Nemotron Ultra 253B | nvidia | 128,000 | |
| llama-3_2-nemoretriever-300m-embed-v1 | nvidia | 32,768 | |
| nv-embedcode-7b-v1 | nvidia | 32,768 | |
| llama-3.1-nemotron-safety-guard-8b-v3 | nvidia | 128,000 | |
| nemotron-mini-4b-instruct | nvidia | 128,000 | |
| cosmos-predict1-5b | nvidia | 0 | |
| nemotron-content-safety-reasoning-4b | nvidia | 128,000 | |
| riva-translate-4b-instruct-v1_1 | nvidia | 128,000 | |
| nvidia-nemotron-nano-9b-v2 | nvidia | 131,072 | |
| gliner-pii | nvidia | 128,000 | |
| Llama 3.1 Nemotron Nano 8B v1 | nvidia | 131,072 | |
| nv-embed-v1 | nvidia | 32,768 | |
| rerank-qa-mistral-4b | nvidia | 128,000 | |
| Nemotron 3.5 Lightning 30B A3B | nvidia | 262,144 | |
| Llama 3.1 Nemotron 70B Instruct | nvidia | 128,000 | |
| Cosmos Reason2 8B | nvidia | 131,072 | |
| Meta: Llama 3.1 8B Instruct | meta | 131,072 | - Input
$0.05 per 1M tokens medium- Input (cached read)
$0.025 per 1M tokens medium- Output
$0.08 per 1M tokens medium
|
| Meta: Llama Guard 4 12B | meta | 163,840 | - Input
$0.18 per 1M tokens medium- Output
$0.18 per 1M tokens medium
|
| Llama 3.2 90B Vision Instruct | meta | 16,000 | |
| Meta: Llama 3.2 3B Instruct | meta | 131,072 | |
| Meta: Llama 3.2 1B Instruct | meta | 60,000 | |
| esmfold | meta | 128,000 | |
| Llama 4 Maverick 17b 128e Instruct | meta | 128,000 | |