NNVIDIA · Released Aug 11, 2026
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...
- Released
- Aug 11 2026
- Context window
- 262K 236K out
- Input / 1M tokens
- $0.07 from Free
- Output / 1M tokens
- $0.20 from Free
Where to run it
17 providers compared
Free to try on Nvidia, AIHubMix, Merge Gateway, Kilo Gateway, Requesty +2 more — free endpoints are often limited-time and rate-limited. Cheapest: Darkbloom, Kilo Gateway at $0.025 / $0.12 per 1M input / output tokens — 81% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Nvidiafree · may be limited-time · nvfp4 · NVFP4 | Free | Free | — | 1M | 66K | 100%24h | Free |
| AIHubMixfree · may be limited-time | Free | Free | — | 262K | 262K | — | Free |
| Merge Gatewayfree · may be limited-time | Free | Free | — | 1M | 262K | — | Free |
| Kilo Gatewayfree · may be limited-time | Free | Free | — | 1M | 66K | — | Free |
| Requestyfree · may be limited-time | Free | Free | — | 1M | 66K | — | Free |
| OpenCodefree · may be limited-time | Free | Free | Free | 262K | 262K | — | Free |
| Vercel AI Gatewayfree · may be limited-time | Free | Free | — | 1M | 65K | — | Free |
| DarkbloomINT4 | $0.025 | $0.12 | $0.012 | 262K | 33K | 100%24h | Cheapest |
| Kilo Gateway | $0.025 | $0.12 | $0.013 | 262K | 236K | — | Cheapest |
| Io Net | $0.047 | $0.13 | $0.023 | 262K | 131K | 99.2%24h | +41% |
| RunInfra | $0.05 | $0.15 | $0.01 | 262K | 33K | — | +54% |
| DeepInfraBF16 | $0.06 | $0.16 | $0.03 | 262K | 33K | 100%24h | +74% |
| NanoGPT | $0.05 | $0.20 | $0.01 | 1M | 66K | — | +79% |
| Vercel AI Gateway | $0.05 | $0.20 | $0.01 | 262K | 131K | — | +79% |
| Fireworks AI | $0.05 | $0.20 | $0.01 | 262K | 262K | — | +79% |
| CoreWeaveBF16 | $0.07 | $0.20 | $0.04 | 262K | 236K | 100%24h | +110% |
| Pioneer | $0.07 | $0.20 | $0.035 | 66K | 4K | — | +110% |
| Nebius Token Factory | $0.06 | $0.24 | $0.06 | 1M | 1M | — | +115% |
| Thinking Machines | $0.18 | $0.49 | $0.037 | 66K | 66K | — | +437% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Nemotron 3.5 Lightning. Scores appear here automatically once it does.
Specs
Details
- Model ID
nvidia/nemotron-3.5-lightning- Developer
- NVIDIA
- Release date
- Aug 11, 2026 ·
- Context window
- 262,144 tokens
- Max output
- 235,929 tokens
- API price
- $0.07 / $0.20 per 1M input / output tokens
- Providers
- 17
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- Yes
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.