NVIDIA · Model
Nemotron 3.5 Lightning pricing, context window and specs
Nemotron 3.5 Lightning costs $0.07 per million input tokens and $0.20 per million output tokens, and reads up to 262,144 tokens per request. By blended price it is the cheapest of NVIDIA’s 4 current models here.
- Input / 1M
- $0.07
- Output / 1M
- $0.20
- Cached / 1M
- $0.04
- Context
- 262,144
- Max output
- Not published
- Released
- 2026-08-11
Estimate your cost with Nemotron 3.5 LightningCompare all NVIDIA modelsCount tokens for Nemotron 3.5 Lightning
Pricing
Nemotron 3.5 Lightning API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.07 | $0.20 |
| Cached input (read) | $0.04 | – |
Output costs 2.9× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 57% of the normal input price.
History
Nemotron 3.5 Lightning price history
Price increase, +49% blended
- Input
- from $0.0469 to $0.07
- +49%
- Output
- from $0.134 to $0.20
- +49%
- Cached input
- from $0.0235 to $0.04
- +71%
Price cut, −4.3% blended
- Input
- from $0.049 to $0.0469
- −4.3%
- Output
- from $0.14 to $0.134
- −4.3%
- Cached input
- from $0.0245 to $0.0235
- −4.3%
Nemotron 3.5 Lightning has open weights, so this is the price of OpenRouter’s top-ranked host, which can move when hosts change rather than because NVIDIA changed its price. Every change across all models is in the AI pricing changes log.
Examples
What Nemotron 3.5 Lightning costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.000163 | $4.94 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.000484 | $7.36 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.00224 | $13.63 |
| Document summariser | 8,000 / 600 | 300 | $0.00068 | $6.21 |
Change any number in the cost calculator.
Context
Context window
Nemotron 3.5 Lightning accepts up to 262,144 tokens per request, roughly 196,608 English words or 393 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $0.0184 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Check whether your text fits Nemotron 3.5 Lightning’s window.
Features
Capabilities
- Image input
- No
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Nemotron 3.5 Lightning model ID
- OpenRouter
nvidia/nemotron-3.5-lightning- Open weights
- nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Use the OpenRouter ID when calling it through OpenRouter; NVIDIA’s own API may name it differently. See the model ID reference for the providers we document.
NVIDIA
Where Nemotron 3.5 Lightning sits in NVIDIA’s line-up
Ranked by blended price (three parts input to one part output, $0.1025 per 1M for Nemotron 3.5 Lightning), it is the cheapest of NVIDIA’s 4 current models here. One step up, Nemotron 3 Nano 30B A3B costs $0.105 (1× as much). It has the same published limits and features as Nemotron 3.5 Lightning. See every NVIDIA model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nemotron 3.5 Lightning (this page) | $0.07 | $0.20 | 262,144 | 2026-08-11 |
| Nemotron 3 Nano 30B A3B | $0.06 | $0.24 | 262,144 | 2025-12-14 |
| Nemotron 3 Super | $0.08 | $0.45 | 262,144 | 2026-03-11 |
| Nemotron 3 Ultra | $0.60 | $2.40 | 202,800 | 2026-06-04 |
NVIDIA’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
Cheaper alternatives
No cheaper model in our data keeps the same essentials.
Current models from major providers, one per provider, that keep tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Ministral 3 3B 2512Mistral$0.10 / $0.10
- Gemma 4 26B A4BGoogle$0.0675 / $0.225
- Qwen3.5-9BQwen$0.10 / $0.15
- Seed 1.6 FlashByteDance Seed$0.075 / $0.30
- GPT-6 LunaOpenAI$0.10 / $0.50
Current models from other major providers, closest blended price.
FAQ
Nemotron 3.5 Lightning questions
How much does Nemotron 3.5 Lightning cost?
Nemotron 3.5 Lightning costs $0.07 per million input tokens and $0.20 per million output tokens, with cached input at $0.04. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.000185. Use the LLM cost calculator for your own workload.
What is Nemotron 3.5 Lightning’s context window?
262,144 tokens, about 196,608 English words or 393 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Nemotron 3.5 Lightning support prompt caching and batch requests?
Yes, cached input is billed at $0.04 per million tokens (57% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Nemotron 3.5 Lightning?
In our data there’s no cheaper model with the same essentials and a comparable context window.
What is the API model ID for Nemotron 3.5 Lightning?
On OpenRouter it is nvidia/nemotron-3.5-lightning. NVIDIA’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
Is Nemotron 3.5 Lightning open source?
Yes, Nemotron 3.5 Lightning has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.