Nemotron 3.5 Lightning vs Inkling Small: cost comparison
Prices updated 2026-10-27 · computed from live provider data
Short answer: Inkling Small is cheaper on a
3:1 input/output blend — Free per million tokens versus
Free, a 0% difference.
Inkling Small offers the larger context window at 1,048,576 tokens, against 1,000,000 for Nemotron 3.5 Lightning.
Head to head
| Nemotron 3.5 Lightning | Inkling Small | |
|---|---|---|
| Input, per 1M tokens | Free | Free |
| Output, per 1M tokens | Free | Free |
| Blended 3:1, per 1M | Free | Free |
| Context window | 1,000,000 | 1,048,576 |
| Vendor | nvidia | thinkingmachines |
Monthly cost at real volumes
| Workload (input / output) | Nemotron 3.5 Lightning | Inkling Small |
|---|---|---|
| 1M in / 250K out | Free | Free |
| 10M in / 2.5M out | Free | Free |
| 100M in / 25M out | Free | Free |
Which should you pick?
Pick Inkling Small when you need the longer context window (1,048,576 vs 1,000,000 tokens). Pick Inkling Small when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.