Nemotron 3 Ultra pricing
$$ Standard$0.60/M input · $3.60/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
Full rate table
| Rate | Price | Unit |
|---|---|---|
| Input | 0.6 | /M tokens |
| Output | 3.5999999999999996 | /M tokens |
| Cache read | 0.19999999999999998 | /M tokens |
What typical work costs
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0024 |
| Long-document summary | 60K tokens in, 2K out | $0.04 |
| Agent working session | 400K tokens in, 40K out across a day | $0.38 |
Price your own workload
- Per call
- $0.0024
- Per month
- $0.24
Compare up to four models at once in the cost calculator.
Frequently asked
What does Nemotron 3 Ultra cost per 1M tokens?
Nemotron 3 Ultra lists at $0.60 per 1M input tokens and $3.60 per 1M output tokens.
Does Nemotron 3 Ultra discount cached input tokens?
Yes. Cached input tokens are billed at $0.20 per 1M, versus $0.60 for fresh input. Prompts that repeat a long prefix (a system prompt, attached files) benefit the most.
What does a typical chat message with Nemotron 3 Ultra cost?
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0024 at list price. Long documents and long replies scale that linearly with token counts.
Is Nemotron 3 Ultra cheaper than Nemotron Nano 30B?
Nemotron Nano 30B has the lower blended price at a 3:1 input:output mix. Nemotron 3 Ultra: $0.60 in / $3.60 out per 1M. Nemotron Nano 30B: $0.05 in / $0.20 out per 1M.
How does idapt bill Nemotron 3 Ultra?
Chat with Nemotron 3 Ultra in idapt is metered per token with transparent, usage-based pricing at the prices shown in the app. Subscriptions include a weekly usage allowance before any balance is touched.
Part of the Nemotron 3 Ultra model page · cheapest models board · price changes