Nemotron 3.5 Lightning 30B A3BOpen weights
NVIDIA · released 2026-08-11
No price from the maker itself is on record for Nemotron 3.5 Lightning 30B A3B. The lowest of 14 providers is Kilo Gateway: $0.025 per 1M input tokens and $0.12 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 262K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| NvidiaOfficialnvidia/ | $0 | $0 | — | Official | Official docs |
KKilo GatewayLowestnvidia/ | $0.025 | $0.12 | $0.0125 | Lowest | Official docs |
RRunInfranvidia/ | $0.05 | $0.15 | $0.01 | Official docs | |
 Vercel AI Gatewaynvidia/ | $0.06 | $0.16 | $0.03 | Official docs | |
NNanoGPTnvidia/ | $0.05 | $0.2 | $0.01 | Official docs | |
NNanoGPTnvidia/ | $0.05 | $0.2 | $0.01 | Official docs | |
 OpenRouternvidia/ | $0.07 | $0.2 | $0.04 | Official docs | |
PPioneernvidia/ | $0.07 | $0.2 | $0.035 | Official docs | |
 CoreWeavenvidia/ | $0.07 | $0.2 | $0.04 | Official docs | |
 Nebius Token Factorynvidia/ | $0.06 | $0.24 | $0.06 | Official docs | |
TThinking Machinesnvidia/ | $0.184 | $0.495 | $0.0368 | Official docs | |
TThinking Machinesnvidia/ | $0.184 | $0.495 | $0.0368 | Official docs |
7 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 AIHubMixnemotron-3.5-lightning-free | $0 | $0 | — | Official docs | |
KKilo Gatewaynvidia/ | $0 | $0 | — | Official docs | |
MMerge Gatewaynvidia/ | $0 | $0 | — | Official docs | |
 OpenCodenemotron-3.5-lightning-free | $0 | $0 | $0 | Official docs | |
| OpenRouternvidia/ | $0 | $0 | — | Official docs | |
RRequestynemotron-3.5-lightning-30b-a3b | $0 | $0 | — | Official docs | |
| Vercel AI Gatewaynvidia/ | $0 | $0 | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 262K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-09
- Open weights
- Yes
- Released
- 2026-08-11
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.