NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.0000006 | $0.600 |
| completion | 0.0000024 | $2.40 |
| input_cache_read | 0.00000012 | $0.120 |
{
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
}21 answersin this database. A round opens every model's answer to the same prompt.