NVIDIAopen weightsNemotron 3.5 Super VL pricing
$0.10 per 1M input tokens and $0.40 per 1M output tokens. In real work that is 0.07¢ per chat answer and 0.24¢ to summarize a 20-page PDF.
What Nemotron 3.5 Super VL 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 | 0.07¢$0.65 / 1,000 | 88 in · 694 out · 909 reasoning | 71 of 336 | estimated |
| Reply to a customer email | 0.03¢$0.31 / 1,000 | 328 in · 98 out · 587 reasoning | 80 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.64¢$6.41 / 1,000 | 104 in · 0 out · 16,000 reasoning | 151 of 336 | estimated |
| Write 10 product descriptions | ≥0.64¢$6.43 / 1,000 | 347 in · 0 out · 16,000 reasoning | 176 of 336 | estimated |
| Translate 1,000 words | 0.07¢$0.66 / 1,000 | 1,396 in · 1,175 out · 136 reasoning | 47 of 336 | estimated |
| Proofread one page (500 words) | 0.08¢$0.81 / 1,000 | 783 in · 676 out · 1,159 reasoning | 84 of 336 | estimated |
| Summarize a 20-page PDF | 0.24¢$2.38 / 1,000 | 13,222 in · 504 out · 2,141 reasoning | 79 of 336 | estimated |
| Extract data from an invoice | 0.09¢$0.92 / 1,000 | 504 in · 565 out · 1,617 reasoning | 93 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.70¢$7.04 / 1,000 | 6,407 in · 0 out · 16,000 reasoning | 85 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.15¢$1.54 / 1,000 | 3,780 in · 981 out · 1,912 reasoning | 86 of 336 | estimated |
| Classify 100 support tickets | 0.35¢$3.51 / 1,000 | 1,474 in · 538 out · 7,879 reasoning | 118 of 336 | estimated |
| Review 500 lines of code | ≥0.69¢$6.89 / 1,000 | 4,912 in · 0 out · 16,000 reasoning | 111 of 336 | estimated |
| Write a SQL query | 0.11¢$1.07 / 1,000 | 178 in · 408 out · 2,225 reasoning | 109 of 336 | estimated |
| Run a 50-step coding agent | 22¢$222 / 1,000 | 2,277,775 in · 15,270 out · 80,850 reasoning | 106 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Nemotron 3.5 Super VL through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
| C Crusoebf16 | $0.10 / $0.40 | $0.08 | 262K | 100% |
 DeepInfrafp4 | $0.10 / $0.40 | $0.08 | 262K | 100% |
 Togetherunknown | $0.15 / $0.50 | $0.02 | 262K | 100% |
| C CoreWeavenvfp4 | $0.15 / $0.50 | $0.02 | 1M | 96% |
| V Venicefp4 | $0.25 / $1.25 | $0.12 | 262K |
Price history
First seen in our price history on Oct 16, 2026 at $0.15 input / $0.50 output. Since then the output price moved from $0.50 to $0.40 per 1M tokens (1 change).
FAQ
How much does Nemotron 3.5 Super VL cost?
Nemotron 3.5 Super VL costs $0.10 per 1 million input tokens and $0.40 per 1 million output tokens, with cached input at $0.08 (list price on Oct 18, 2026). In practice one chat answer costs about 0.07¢ and summarizing a 20-page PDF about 0.24¢.
Where is Nemotron 3.5 Super VL cheapest?
Among 5 providers we track, the lowest list price today is at Crusoe: $0.10 input and $0.40 output per 1M tokens.
Is the Nemotron 3.5 Super VL cost per task measured or estimated?
Estimated: Nemotron 3.5 Super VL was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of NVIDIA. Real usage can differ.