token.app › Compare › Nemotron 3 Super vs Inkling Small
Nemotron 3 Super vs Inkling Small
Inkling Small is 1.3× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| Nemotron 3 Super | Inkling Small | |
|---|---|---|
| Provider | NVIDIA | Thinkingmachines |
| Input $/1M | $0.300 | $0.450 |
| Output $/1M | $2.40 | $1.20 |
| Blended $/1M | $0.825 | $0.637 |
| Context window | 262K | 524K |
| Max output | 236K | 262K |
| Released | Mar 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose Nemotron 3 Super if…
- No clear advantage on the data we hold.
Choose Inkling Small if…
- Costs less per token — $0.637 vs $0.825 blended
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, Nemotron 3 Super or Inkling Small?
We do not hold independently-run benchmark scores covering both Nemotron 3 Super and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Nemotron 3 Super cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $0.825 per million tokens blended at 3:1 input:output. Input alone: $0.300 vs $0.450. Output alone: $2.40 vs $1.20.
What context windows do Nemotron 3 Super and Inkling Small have?
Nemotron 3 Super: 262,144 tokens. Inkling Small: 524,288 tokens.
Who makes Nemotron 3 Super and Inkling Small?
Nemotron 3 Super is made by NVIDIA. Inkling Small is made by Thinkingmachines.
Related comparisons