token.app › Compare › Gemma 3n 4B vs Inkling Small
Gemma 3n 4B vs Inkling Small
Gemma 3n 4B is 8.5× 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
| Gemma 3n 4B | Inkling Small | |
|---|---|---|
| Provider | Thinkingmachines | |
| Input $/1M | $0.060 | $0.450 |
| Output $/1M | $0.120 | $1.20 |
| Blended $/1M | $0.075 | $0.637 |
| Context window | 33K | 524K |
| Max output | — | 262K |
| Released | May 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose Gemma 3n 4B if…
- Costs less per token — $0.075 vs $0.637 blended
Choose Inkling Small if…
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 3n 4B or Inkling Small?
We do not hold independently-run benchmark scores covering both Gemma 3n 4B and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 3n 4B cheaper than Inkling Small?
Gemma 3n 4B is cheaper: $0.075 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.060 vs $0.450. Output alone: $0.120 vs $1.20.
What context windows do Gemma 3n 4B and Inkling Small have?
Gemma 3n 4B: 32,768 tokens. Inkling Small: 524,288 tokens.
Who makes Gemma 3n 4B and Inkling Small?
Gemma 3n 4B is made by Google. Inkling Small is made by Thinkingmachines.