Nemotron 3.5 Lightning pricing & price history
Nemotron 3.5 Lightning by NVIDIA costs $0.07 per 1M input tokens and $0.20 per 1M output tokens, with a 262K token context window. The cheapest provider currently charges $0.025 input / $0.12 output.
Price history
| Date | Input | Output |
|---|---|---|
| 2026-10-10 | $0.0469 → $0.07 +49% | $0.13 → $0.20 +49% |
| 2026-10-10 | $0.07 → $0.0469 -33% | $0.20 → $0.13 -33% |
| 2026-10-09 | $0.049 → $0.07 +43% | $0.14 → $0.20 +43% |
| 2026-10-07 | $0.06 → $0.049 -18% | $0.16 → $0.14 -12% |
| 2026-10-05 | $0.0595 → $0.06 +1% | $0.17 → $0.16 -6% |
| 2026-10-03 | $0.06 → $0.0595 -1% | $0.16 → $0.17 +6% |
| 2026-10-02 | $0.0595 → $0.06 +1% | $0.17 → $0.16 -6% |
| 2026-10-01 | $0.08 → $0.0595 -26% | $0.20 → $0.17 -15% |
| 2026-09-26 | $0.07 → $0.08 +14% | $0.20 → $0.20 |
| 2026-09-25 | $0.08 → $0.07 -12% | $0.20 → $0.20 |
No real-traffic data for NVIDIA's own API on this model (it may not be served directly); the table below covers third-party hosts and says nothing about the official API.
Which platform runs Nemotron 3.5 Lightning most reliably
5 platformsBy 24-hour real-traffic success rate, Wafer is the most stable; Darkbloom is the cheapest.
| Platform | Last 30 days | Stability | 24 h | 30 min | |
|---|---|---|---|---|---|
| Wafer most stable | Collecting data | 100% | 100% | ||
| Io Net | Collecting data | 100% | 100% | ||
| DeepInfra | Collecting data | 100% | 100% | ||
| CoreWeave | Collecting data | 100% | 100% | ||
| Darkbloom | Collecting data | 99.1% | 100% |
Success rates come from real API traffic routed to each platform (public OpenRouter data), not our probes; each daily bar is the average of that day's samples. Green ≥ 99.5 %, yellow ≥ 97 %, orange ≥ 90 %, red < 90 %. Updated 27d ago.
Cost calculator
Cheaper alternatives to Nemotron 3.5 Lightning
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
 Lyria 3 Pro Preview Google | Free | Free | 1M | — | compare |
Lyria 3 Clip Preview Google | Free | Free | 1M | — | compare |
 Ling 3.0 Tiny inclusionAI | $0.015 | $0.045 | 262K | — | compare |
 Llama 3.1 8B Instruct Meta Llama | $0.02 | $0.04 | 131K | — | compare |
 Mistral Nemo Mistral AI | $0.029 | $0.03 | 131K | — | compare |
 Summarize Scaledown | $0.04 | Free | 1M | — | compare |
Extract Scaledown | $0.04 | Free | 1M | — | compare |
Ling 3.0 Flash inclusionAI | $0.021 | $0.063 | 262K | — | compare |
Using a relay or third-party API?
Check for free whether it really serves Nemotron 3.5 Lightning: output fingerprint, tokenizer and billing evidence, results in 1–3 minutes.
About 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...
FAQ
How much does Nemotron 3.5 Lightning cost?
Nemotron 3.5 Lightning by NVIDIA costs $0.07 per 1M input tokens and $0.20 per 1M output tokens, with a 262K token context window. The cheapest provider currently charges $0.025 input / $0.12 output. A typical request with 2,000 input and 500 output tokens costs about $0.0002.
What is the context window of Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning supports up to 262,144 tokens of context and up to 235,929 output tokens per request.
Has Nemotron 3.5 Lightning’s price changed?
Yes. ModelBank recorded 10 price changes; the latest on 2026-10-10.
Is Nemotron 3.5 Lightning being deprecated?
No retirement date has been announced for Nemotron 3.5 Lightning as of 2026-11-12.
What are cheaper alternatives to Nemotron 3.5 Lightning?
Cheaper options include Lyria 3 Pro Preview (Free/Free), Lyria 3 Clip Preview (Free/Free), Ling 3.0 Tiny ($0.015/$0.045), Llama 3.1 8B Instruct ($0.02/$0.04).