Nemotron 3.5 Lightning 30B A3B
As of Nov 22, 2026, the cheapest Nemotron 3.5 Lightning 30B A3B API price is $0.02 per 1M input tokens (Kilo Gateway) and $0.096 per 1M output tokens (Kilo Gateway). Nemotron 3.5 Lightning 30B A3B is offered by 11 providers in the nemotron-lightning family, open weights, reasoning enabled. 5 providers list it as a free-tier offer.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| Kilo Gatewayopennvidia/nemotron-3.5-lightning | Cheapest$0.02 | Cheapest$0.096 | $0.01 | — | 262k | yesterdayout −20% |
| RunInfraopennvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | $0.05 | $0.15 | $0.01 | — | 262k | — |
| Requestynemotron-lightning-3.5-30b-a3b | $0.05 | $0.2 | $0.01 | — | 262k | — |
| OpenRouteropennvidia/nemotron-3.5-lightning | $0.07 | $0.2 | $0.04 | — | 1.0M | 42d ago |
| Pioneeropennvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | $0.07 | $0.2 | $0.035 | $0.07 | 66k | 32d ago |
| Nebius Token Factoryopennvidia/Nemotron-3_5-Lightning | $0.06 | $0.24 | $0.03 | — | 1.0M | — |
| Thinking Machinesopennvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | $0.184 | $0.495 | $0.0368 | — | 66k | — |
| Thinking Machinesopennvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144 | $0.184 | $0.495 | $0.0368 | — | 262k | — |
| AIHubMixfreenemotron-3.5-lightning-free | free | free | — | — | 262k | — |
| InferAllfreenvidia/nemotron-3.5-lightning-30b-a3b | free | free | — | — | 262k | — |
| Merge Gatewayfreenvidia/nemotron-3.5-lightning-30b-a3b | free | free | — | — | 1.0M | — |
| Nvidiafreenvidia/nemotron-3.5-lightning-30b-a3b | free | free | — | — | 262k | — |
| Requestyfreenemotron-3.5-lightning-30b-a3b | free | free | — | — | 1.0M | — |
Nemotron 3.5 Lightning 30B A3B price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 3 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Kilo Gateway | $0.025 → $0.02 | $0.12 → $0.096 | −20% | |
| Pioneer | $0.5 → $0.07 | $0.5 → $0.2 | −60% | |
| OpenRouter | $0.0469 → $0.07 | $0.134 → $0.2 | +49.3% | |
| Kilo Gateway | $0.039 → $0.025 | $0.18 → $0.12 | −33.3% | |
| OpenRouter | $0.049 → $0.0469 | $0.14 → $0.134 | −4.3% | |
| OpenRouter | $0.06 → $0.049 | $0.16 → $0.14 | −12.5% | |
| OpenRouter | $0.0595 → $0.06 | $0.17 → $0.16 | −5.9% | |
| OpenRouter | $0.06 → $0.0595 | $0.16 → $0.17 | +6.3% | |
| OpenRouter | $0.0595 → $0.06 | $0.17 → $0.16 | −5.9% | |
| OpenRouter | $0.06 → $0.0595 | $0.16 → $0.17 | +6.3% | |
| OpenRouter | $0.08 → $0.06 | $0.2 → $0.16 | −20% | |
| Kilo Gateway | $0.065 → $0.039 | $0.18 | −40% | |
| OpenRouter | $0.07 → $0.08 | $0.2 | +14.3% | |
| Kilo Gateway | $0.04 → $0.065 | $0.18 | +62.5% | |
| Kilo Gateway | $0.065 → $0.04 | $0.18 | −38.5% | |
| OpenRouter | $0.08 → $0.07 | $0.2 | −12.5% | |
| Kilo Gateway | $0.08 → $0.065 | $0.2 → $0.18 | −10% |
Nemotron 3.5 Lightning 30B A3B pricing FAQ
What is the cheapest Nemotron 3.5 Lightning 30B A3B API?
As of Nov 22, 2026, Kilo Gateway has the lowest Nemotron 3.5 Lightning 30B A3B output price at $0.096 per 1M tokens, and Kilo Gateway has the lowest input price at $0.02 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Nemotron 3.5 Lightning 30B A3B?
11 providers list Nemotron 3.5 Lightning 30B A3B on Sovyron; 8 of them sell it at a metered per-token price.
Is Nemotron 3.5 Lightning 30B A3B free?
5 providers list a free-tier offer: AIHubMix, InferAll, Merge Gateway, Nvidia, Requesty. Free tiers usually have rate limits.
What is the context window of Nemotron 3.5 Lightning 30B A3B?
Nemotron 3.5 Lightning 30B A3B supports a 1.0M-token context window and up to 1.0M output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—