token.app › Compare › Gemma 3 4B vs Inkling Small
Gemma 3 4B vs Inkling Small
Gemma 3 4B is 10× 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 3 4B | Inkling Small | |
|---|---|---|
| Provider | Thinkingmachines | |
| Input $/1M | $0.050 | $0.450 |
| Output $/1M | $0.100 | $1.20 |
| Blended $/1M | $0.063 | $0.637 |
| Context window | 131K | 524K |
| Max output | 16K | 262K |
| Released | Mar 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose Gemma 3 4B if…
- Costs less per token — $0.063 vs $0.637 blended
Choose Inkling Small if…
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 3 4B or Inkling Small?
We do not hold independently-run benchmark scores covering both Gemma 3 4B and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 3 4B cheaper than Inkling Small?
Gemma 3 4B is cheaper: $0.063 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.050 vs $0.450. Output alone: $0.100 vs $1.20.
What context windows do Gemma 3 4B and Inkling Small have?
Gemma 3 4B: 131,072 tokens. Inkling Small: 524,288 tokens.
Who makes Gemma 3 4B and Inkling Small?
Gemma 3 4B is made by Google. Inkling Small is made by Thinkingmachines.