Nemotron 3 Ultra API Pricing
NVIDIA · context window 262K · prices updated 2026-09-20
Where Nemotron 3 Ultra sits on price
At $2.40 per million output tokens, Nemotron 3 Ultra is a mid tier model — 1.2× the median output price of $2.00, which puts it cheaper than 45% and pricier than 55% of the models we track. It is the most expensive of the 5 NVIDIA models we track. Output costs 4.0× input, the usual spread — trim both, starting with the answer length.
Cached input is 80% cheaper. On an input-heavy workload you need roughly a 31% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Nemotron 3 Ultra
These three workloads are the ones teams actually run on a mid-priced model — a $2.40/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0064 | $95.40 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.003 | $900 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0007 | $19.80 |
Model your exact traffic in the API cost calculator — it preloads Nemotron 3 Ultra with caching and batch options.
Nemotron 3 Ultra price history
NVIDIA last cut Nemotron 3 Ultra's output price on Sep 19, 2026 (-23% per output token), from $0.625/$3.13 to $0.6/$2.40 per 1M in/out. That is one of 7 repricings in the 49 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 2, 2026 (tracking began) | $0.6 | $3.60 | — |
| Aug 28, 2026 | $0.5 | $2.20 | -39% |
| Sep 2, 2026 | $0.625 | $3.13 | +42% |
| Sep 3, 2026 | $0.6 | $2.40 | -23% |
| Sep 4, 2026 | $0.625 | $3.13 | +30% |
| Sep 14, 2026 | $0.6 | $2.40 | -23% |
| Sep 16, 2026 | $0.625 | $3.13 | +30% |
| Sep 19, 2026 | $0.6 | $2.40 | -23% |
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
Nemotron 3 Ultra vs Qwen3 VL 30B A3B Thinking
The closest-priced alternative from another vendor is Qwen3 VL 30B A3B Thinking (Alibaba (Qwen)) — priced within a rounding error on output, with $0.4 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Qwen3 VL 30B A3B Thinking pricing →Cheaper alternatives
More NVIDIA models
Frequently asked questions
› How much does the Nemotron 3 Ultra API cost?
Nemotron 3 Ultra costs $0.6 per million input tokens and $2.40 per million output tokens, with cached input at $0.12 per million (80% cheaper). That works out to roughly 416,667 output tokens per dollar.
› What does the support chatbot workload cost on Nemotron 3 Ultra?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0064 per request and $95.40 per month on Nemotron 3 Ultra. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Nemotron 3 Ultra's 262K context window?
Sending 262K of input in a single request costs $0.1573 at $0.6 per million tokens — before any output. With prompt caching that same fill drops to about $0.0315 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Nemotron 3 Ultra worth the price?
Nemotron 3 Ultra sits in the middle of the market (5 of 5 by price within NVIDIA). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.