token.app › Compare › Nemotron 3 Ultra vs Inkling Small
Nemotron 3 Ultra vs Inkling Small
Inkling Small is 2.1× 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 Ultra | Inkling Small | |
|---|---|---|
| Provider | NVIDIA | Thinkingmachines |
| Input $/1M | $0.600 | $0.450 |
| Output $/1M | $3.60 | $1.20 |
| Blended $/1M | $1.35 | $0.637 |
| Context window | 512K | 524K |
| Max output | — | 262K |
| Released | Jun 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose Nemotron 3 Ultra if…
- No clear advantage on the data we hold.
Choose Inkling Small if…
- Costs less per token — $0.637 vs $1.35 blended
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, Nemotron 3 Ultra or Inkling Small?
We do not hold independently-run benchmark scores covering both Nemotron 3 Ultra and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Nemotron 3 Ultra cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $1.35 per million tokens blended at 3:1 input:output. Input alone: $0.600 vs $0.450. Output alone: $3.60 vs $1.20.
What context windows do Nemotron 3 Ultra and Inkling Small have?
Nemotron 3 Ultra: 512,288 tokens. Inkling Small: 524,288 tokens.
Who makes Nemotron 3 Ultra and Inkling Small?
Nemotron 3 Ultra is made by NVIDIA. Inkling Small is made by Thinkingmachines.
Related comparisons