NVIDIANemotron 3.5 Lightning
Not yet ranked: too few independent results so far. Released 11 Aug 2026.
- Blended price
- $0.095/M
- $0.060 in · $0.200 out
- Output speed
- 277 tok/s
- First answer
- 7.89 s
- first token 1.12 s
- Context
- 1M
- Knowledge56
- Long context56
- Composite46
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 74.3%#250 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 10.6%#248 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode (AA)not in index | 32.1%#143 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -17.7#174 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 60.3%#216 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 13.6#241 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| CoreWeave | 159 tok/s | 0.15 s | $0.100 | $0.250 | 262k | bf16 |
| DeepInfra | 34 tok/s | 2.08 s | $0.080 | $0.200 | 262k | bf16 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.060 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | $0.0001 | 9.0 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0008 | $0.0008 | 10.1 s |
| Code edit | 6,000 / 1,500 | $0.0007 | $0.0007 | 13.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.0044 | $0.0044 | 22.3 s |
| Structured extraction | 2,000 / 200 | $0.0002 | $0.0002 | 8.6 s |
See also
Data as of 9 Sept 2026. Compare with another model.