token.app › Compare › Gemma 3n 4B vs Kimi K3
Gemma 3n 4B vs Kimi K3
Gemma 3n 4B is 80× cheaper per token on a blended 3:1 basis. Kimi K3 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Gemma 3n 4B | Kimi K3 | |
|---|---|---|
| Provider | Moonshot AI | |
| Input $/1M | $0.060 | $3.00 |
| Output $/1M | $0.120 | $15.00 |
| Blended $/1M | $0.075 | $6.00 |
| Context window | 33K | 1.0M |
| Max output | — | — |
| Released | May 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose Gemma 3n 4B if…
- Costs less per token — $0.075 vs $6.00 blended
Choose Kimi K3 if…
- Larger context window (1.0M)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 3n 4B or Kimi K3?
We do not hold independently-run benchmark scores covering both Gemma 3n 4B and Kimi K3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 3n 4B cheaper than Kimi K3?
Gemma 3n 4B is cheaper: $0.075 versus $6.00 per million tokens blended at 3:1 input:output. Input alone: $0.060 vs $3.00. Output alone: $0.120 vs $15.00.
What context windows do Gemma 3n 4B and Kimi K3 have?
Gemma 3n 4B: 32,768 tokens. Kimi K3: 1,048,576 tokens.
Who makes Gemma 3n 4B and Kimi K3?
Gemma 3n 4B is made by Google. Kimi K3 is made by Moonshot AI.