nvidia
NVIDIA: Nemotron 3 Ultra (batch) API Pricing
NVIDIA: Nemotron 3 Ultra (batch) costs $0.600 per 1M input tokens and $3.60 per 1M output tokens (cache reads: $0.200). Context window: 512K. Prices verified 2026-08-23 · source
Input / 1M tokens
$0.600
Output / 1M tokens
$3.60
Context window
512K
Max output
—
What would NVIDIA: Nemotron 3 Ultra (batch) cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $19.20 |
| Coding agent | 5,000 | 8,000 / 2,000 | $60.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $126.00 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $31.20 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About NVIDIA: Nemotron 3 Ultra (batch)
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...