NVIDIAopen weightsNemotron 3 Nano 30B A3B pricing
$0.06 per 1M input tokens and $0.24 per 1M output tokens. In real work that is 0.04¢ per chat answer and 0.14¢ to summarize a 20-page PDF.
What Nemotron 3 Nano 30B A3B costs per task
Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.04¢$0.39 / 1,000 | 88 in · 694 out · 909 reasoning | 45 of 336 | estimated |
| Reply to a customer email | 0.02¢$0.18 / 1,000 | 328 in · 98 out · 587 reasoning | 49 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.38¢$3.85 / 1,000 | 104 in · 0 out · 16,000 reasoning | 108 of 336 | estimated |
| Write 10 product descriptions | ≥0.39¢$3.86 / 1,000 | 347 in · 0 out · 16,000 reasoning | 123 of 336 | estimated |
| Translate 1,000 words | 0.04¢$0.40 / 1,000 | 1,396 in · 1,175 out · 136 reasoning | 26 of 336 | estimated |
| Proofread one page (500 words) | 0.05¢$0.49 / 1,000 | 783 in · 676 out · 1,159 reasoning | 51 of 336 | estimated |
| Summarize a 20-page PDF | 0.14¢$1.43 / 1,000 | 13,222 in · 504 out · 2,141 reasoning | 36 of 336 | estimated |
| Extract data from an invoice | 0.06¢$0.55 / 1,000 | 504 in · 565 out · 1,617 reasoning | 57 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.42¢$4.22 / 1,000 | 6,407 in · 0 out · 16,000 reasoning | 56 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.09¢$0.92 / 1,000 | 3,780 in · 981 out · 1,912 reasoning | 46 of 336 | estimated |
| Classify 100 support tickets | 0.21¢$2.11 / 1,000 | 1,474 in · 538 out · 7,879 reasoning | 73 of 336 | estimated |
| Review 500 lines of code | ≥0.41¢$4.13 / 1,000 | 4,912 in · 0 out · 16,000 reasoning | 64 of 336 | estimated |
| Write a SQL query | 0.06¢$0.64 / 1,000 | 178 in · 408 out · 2,225 reasoning | 59 of 336 | estimated |
| Run a 50-step coding agent | 16¢$160 / 1,000 | 2,277,775 in · 15,270 out · 80,850 reasoning | 79 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Nemotron 3 Nano 30B A3B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Novitafp4 | $0.05 / $0.20 | - | 262K | 100% |
 Nebiusfp8 | $0.06 / $0.24 | - | 262K | 100% |
Price history
First seen in our price history on Dec 28, 2025 at $0.06 input / $0.24 output. Since then the output price moved from $0.24 to $0.24 per 1M tokens (2 changes).
FAQ
How much does Nemotron 3 Nano 30B A3B cost?
Nemotron 3 Nano 30B A3B costs $0.06 per 1 million input tokens and $0.24 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.04¢ and summarizing a 20-page PDF about 0.14¢.
Where is Nemotron 3 Nano 30B A3B cheapest?
Among 2 providers we track, the lowest list price today is at Novita: $0.05 input and $0.20 output per 1M tokens.
Is the Nemotron 3 Nano 30B A3B cost per task measured or estimated?
Estimated: Nemotron 3 Nano 30B A3B was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of NVIDIA. Real usage can differ.