NVIDIAGeneralReleased 11 August 2026
Nemotron 3.5 Lightning pricing, context and benchmark
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
262K
Input context
236K
Output context
$0.025
Official input
$0.12
Official output
6
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Nemotron 3.5 Lightning |
| Model ID | nvidia/nemotron-3.5-lightning |
| Provider | NVIDIA |
| Release date | 11 August 2026 |
| Status | Generally available |
| Input context | 262,144 tokens |
| Output context | 235,929 tokens |
| Official input pricing | $0.025 per 1M tokens |
| Official output pricing | $0.12 per 1M tokens |
| Cache read pricing | $0.04 per 1M tokens (33% off input) |
| Market input pricing | $0.025 per 1M (cheapest route) |
| Market output pricing | $0.12 per 1M (cheapest route) |
| Highest route pricing | $0.05 in, $0.2 out per 1M |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 4 endpoints |
| Artificial Analysis index | 6 (#7 of 10) |
| Speed | 243 tokens/s, 13.45s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.025 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is Nemotron 3.5 Lightning?
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
It is suited for high-throughput agentic workloads and specialized tasks that...
Nemotron 3.5 Lightning carries a 262K token window, uses the Other tokenizer and is served by NVIDIA. On Hoodgen it sits in the General tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released11 August 2026
| Property | Nemotron 3 Nano Omni (free) | Nemotron 3.5 Lightning | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 256K | 262K | Changed |
| Max output | 66K | 236K | Changed |
| Input price | Free | $0.025 | Higher |
| Output price | Free | $0.12 | Higher |
| Input modalities | text, audio, image, video | text | Unchanged |
| AA index | n/a | 6 | Newer benchmark run |
04 · Capabilities
Features and capabilities
⚡
Prompt caching
Cached input costs $0.04 per million instead of $0.025, so stable prefixes get cheaper.
06 · Benchmarks
Benchmark results and performance
Artificial Analysis Intelligence Index v5.0.1 blends nine evaluations. Nemotron 3.5 Lightning scores 6 , ranking #7 of 10.
Intelligence index
6
#7 of 10
Cost per task
$0.31
weighted average per index task
Time per task
4.5m
inference time
Output speed
243
tokens per second
Index score and cost per task
Scale: index 0 to 70, cost 0 to $20. Sub scores are not published per evaluation, so none are invented here.
07 · Use cases
What can you do with Nemotron 3.5 Lightning?
Everyday writing
Drafts, rewrites, summaries and replies.
Research
Source material condensed with the key numbers kept.
Chat
General questions where latency and cost both matter.
Tooling inside Hoodgen
Writer, Humanizer, Coding and the rest of the tool suite.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.04 per million instead of $0.025, a 33% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Nemotron 3.5 Lightning pricing
Official pricing
List price
$0.025 / 1M in
$0.12 / 1M out
- $0.04 cached input
- 262K context
- text input
Cheapest route
$0.025 / 1M in
$0.12 / 1M out
- 4 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$0.05 / 1M in
$0.2 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Darkbloom | standard | $0.025 | $0.12 | $0.013 | 98.7% |
| Fireworks | standard | $0.05 | $0.2 | $0.01 | 99.0% |
| DeepInfra | standard | $0.06 | $0.16 | $0.03 | 100.0% |
| CoreWeave | standard | $0.07 | $0.2 | $0.04 | 99.9% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0005 | $0.27 | 252 |
| List price | $0.0009 | $0.43 | 410 |
| Highest route | $0.0013 | $0.65 | 618 |
10 · Developers
API and developer information
| Model ID | nvidia/nemotron-3.5-lightning |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 262,144 |
| Max completion tokens | 235,929 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3.5-lightning",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 235,929 tokens per request. Long deliverables have to be chunked. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Nemotron 3.5 Lightning vs other NVIDIA models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Nemotron 3.5 Lightning | 262K | $0.025 | $0.12 | 6 | 2026 |
| Nemotron 3.5 Super VL | 1.05M | $0.06 | $0.35 | 14 | Oct 2026 |
| Nemotron 3 Nano 30B A3B | 262K | $0.06 | $0.24 | n/a | 2025 |
| Nemotron 3.5 Super VL (free) | 1M | Free | Free | n/a | Oct 2026 |
| Nemotron 3 Nano Omni (free) | 256K | Free | Free | n/a | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to NVIDIA and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Nemotron 3.5 Lightning questions, answered
Nemotron 3.5 Lightning is a general model from NVIDIA, released 11 August 2026. NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
✦
Start chatting with Nemotron 3.5 Lightning
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.