Nemotron 3.5 Lightning API Pricing
NVIDIA · context window 262K · prices updated 2026-08-24
Where Nemotron 3.5 Lightning sits on price
At $0.2 per million output tokens, Nemotron 3.5 Lightning is a budget tier model — 11.3× cheaper than the median output price of $2.25, which puts it in the cheapest 10% of everything we track. It is the cheapest of the 5 NVIDIA models we track. Output is only 2.5× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.
Cached input is 50% cheaper. On an input-heavy workload you need roughly a 50% 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 3.5 Lightning
These three workloads are the ones teams actually run on a budget-priced model — a $0.2/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. | $0 | $216 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0001 | $2.10 |
| Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. | $0.0003 | $102 |
Model your exact traffic in the API cost calculator — it preloads Nemotron 3.5 Lightning with caching and batch options.
Nemotron 3.5 Lightning price history
NVIDIA last cut Nemotron 3.5 Lightning's output price on Aug 17, 2026 (-20% per output token), from $0.1/$0.25 to $0.08/$0.2 per 1M in/out. That is the only repricing in the 12 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 12, 2026 (tracking began) | $0.1 | $0.25 | — |
| Aug 17, 2026 | $0.08 | $0.2 | -20% |
Change-points from our daily price snapshots (tracking since Aug 12, 2026; intraday moves between snapshots are not captured).
Nemotron 3.5 Lightning vs Qwen2.5 7B Instruct
The closest-priced alternative from another vendor is Qwen2.5 7B Instruct (Alibaba (Qwen)) — priced within a rounding error on output, with $0.02 more 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 Qwen2.5 7B Instruct pricing →Cheaper alternatives
More NVIDIA models
Frequently asked questions
› How much does the Nemotron 3.5 Lightning API cost?
Nemotron 3.5 Lightning costs $0.08 per million input tokens and $0.2 per million output tokens, with cached input at $0.04 per million (50% cheaper). That works out to roughly 5,000,000 output tokens per dollar.
› What does the high-volume classification workload cost on Nemotron 3.5 Lightning?
High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $216 per month on Nemotron 3.5 Lightning. Short output, huge volume: the input price dominates the bill.
› What does it cost to fill Nemotron 3.5 Lightning's 262K context window?
Sending 262K of input in a single request costs $0.021 at $0.08 per million tokens — before any output. With prompt caching that same fill drops to about $0.0105 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Nemotron 3.5 Lightning worth the price?
Nemotron 3.5 Lightning is in the cheapest end of the market — cheaper than 94% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.