NVIDIA: Nemotron 3.5 Lightning
nvidia/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...
Modalities
In / Out Price
$0.049 / $0.14 per 1M
Context
262K
Released
Aug 11, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Darkbloomint4 | 262K | $0.039 | $0.18 | $0.0195 | — | — | 100.00% |
 Io Net | 262K | $0.049 | $0.14 | $0.0245 | — | — | 100.00% |
 DeepInfrabf16 | 262K | $0.06 | $0.16 | $0.03 | — | — | 100.00% |
 Phala | 262K | $0.07 | $0.20 | $0.04 | — | — | 100.00% |
 CoreWeavebf16 | 262K | $0.07 | $0.20 | $0.04 | — | — | 100.00% |