token.app › Compare › Gemma 3n 4B vs GPT-5.6 Luna
Gemma 3n 4B vs GPT-5.6 Luna
Gemma 3n 4B is 3.0× cheaper per token on a blended 3:1 basis. GPT-5.6 Luna accepts the larger context window (1.1M).
Head to head
Blended price uses a 3:1 input:output mix
| Gemma 3n 4B | GPT-5.6 Luna | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $0.060 | $0.100 |
| Output $/1M | $0.120 | $0.600 |
| Blended $/1M | $0.075 | $0.225 |
| Context window | 33K | 1.1M |
| Max output | — | 128K |
| Released | May 2025 | Jul 2026 |
| Licence | Open weights | Proprietary |
Choose Gemma 3n 4B if…
- Costs less per token — $0.075 vs $0.225 blended
- Open weights — self-hostable
Choose GPT-5.6 Luna if…
- Larger context window (1.1M)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 3n 4B or GPT-5.6 Luna?
We do not hold independently-run benchmark scores covering both Gemma 3n 4B and GPT-5.6 Luna, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Gemma 3n 4B cheaper than GPT-5.6 Luna?
Gemma 3n 4B is cheaper: $0.075 versus $0.225 per million tokens blended at 3:1 input:output. Input alone: $0.060 vs $0.100. Output alone: $0.120 vs $0.600.
What context windows do Gemma 3n 4B and GPT-5.6 Luna have?
Gemma 3n 4B: 32,768 tokens. GPT-5.6 Luna: 1,050,000 tokens.
Who makes Gemma 3n 4B and GPT-5.6 Luna?
Gemma 3n 4B is made by Google. GPT-5.6 Luna is made by OpenAI.