Nemotron 3.5 Lightning
NVIDIA released 2026-08-11
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +28.2 higher and costs 5% less ($0.105/M against $0.110/M) on this workload — and it does everything this model does.
Ling-3.0-flash is cheaper still (71% less) but drops 131K → 33K max output.
The same model via free is 100% cheaper (free/M) — same weights, different latency.
Every price dimension
| Input | $0.080/M |
|---|---|
| Output | $0.200/M |
| Cached input | $0.040/M |
Independent scores
| Intelligence | 23.6 |
|---|---|
| Coding | 26.8 |
| Agentic | 13.8 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 262K |
|---|---|
| Max output | 131K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
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...