NVIDIAopen weightsNemotron 3.5 Lightning pricing
$0.07 per 1M input tokens and $0.20 per 1M output tokens. In real work that is 0.03¢ per chat answer and 0.15¢ to summarize a 20-page PDF.
What Nemotron 3.5 Lightning 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 | 0.03¢$0.33 / 1,000 | 88 in · 694 out · 909 reasoning | 31 of 336 | estimated |
| Reply to a customer email | 0.02¢$0.16 / 1,000 | 328 in · 98 out · 587 reasoning | 39 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.32¢$3.21 / 1,000 | 104 in · 0 out · 16,000 reasoning | 94 of 336 | estimated |
| Write 10 product descriptions | ≥0.32¢$3.22 / 1,000 | 347 in · 0 out · 16,000 reasoning | 108 of 336 | estimated |
| Translate 1,000 words | 0.04¢$0.36 / 1,000 | 1,396 in · 1,175 out · 136 reasoning | 20 of 336 | estimated |
| Proofread one page (500 words) | 0.04¢$0.42 / 1,000 | 783 in · 676 out · 1,159 reasoning | 38 of 336 | estimated |
| Summarize a 20-page PDF | 0.15¢$1.45 / 1,000 | 13,222 in · 504 out · 2,141 reasoning | 37 of 336 | estimated |
| Extract data from an invoice | 0.05¢$0.47 / 1,000 | 504 in · 565 out · 1,617 reasoning | 47 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.36¢$3.65 / 1,000 | 6,407 in · 0 out · 16,000 reasoning | 44 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.08¢$0.84 / 1,000 | 3,780 in · 981 out · 1,912 reasoning | 41 of 336 | estimated |
| Classify 100 support tickets | 0.18¢$1.79 / 1,000 | 1,474 in · 538 out · 7,879 reasoning | 64 of 336 | estimated |
| Review 500 lines of code | ≥0.35¢$3.54 / 1,000 | 4,912 in · 0 out · 16,000 reasoning | 48 of 336 | estimated |
| Write a SQL query | 0.05¢$0.54 / 1,000 | 178 in · 408 out · 2,225 reasoning | 48 of 336 | estimated |
| Run a 50-step coding agent | 11¢$113 / 1,000 | 2,277,775 in · 15,270 out · 80,850 reasoning | 63 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Nemotron 3.5 Lightning through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| D Darkbloomint4 | $0.025 / $0.12 | $0.013 | 262K | 100% |
| I Io Netunknown | $0.047 / $0.13 | $0.023 | 262K | |
 DeepInfrabf16 | $0.06 / $0.16 | $0.03 | 262K | 100% |
| C CoreWeavebf16 | $0.07 / $0.20 | $0.04 | 262K | 100% |
Price history
First seen in our price history on Aug 14, 2026 at $0.10 input / $0.25 output. Since then the output price moved from $0.25 to $0.20 per 1M tokens (4 changes).
FAQ
How much does Nemotron 3.5 Lightning cost?
Nemotron 3.5 Lightning costs $0.07 per 1 million input tokens and $0.20 per 1 million output tokens, with cached input at $0.04 (list price on Oct 18, 2026). In practice one chat answer costs about 0.03¢ and summarizing a 20-page PDF about 0.15¢.
Where is Nemotron 3.5 Lightning cheapest?
Among 4 providers we track, the lowest list price today is at Darkbloom: $0.025 input and $0.12 output per 1M tokens.
Is the Nemotron 3.5 Lightning cost per task measured or estimated?
Estimated: Nemotron 3.5 Lightning was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of NVIDIA. Real usage can differ.