Gemma 3 4B vs Gemma 4 31B
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Gemma 3 4B is 4.0× cheaper than Gemma 4 31B on a typical 3:1 input/output mix. Gemma 4 31B has the larger context window (262K vs 131K).
| Gemma 3 4B | Gemma 4 31B | |
|---|---|---|
| Input price / 1M | $0.05 | $0.20 |
| Output price / 1M | $0.10 | $0.40 |
| Blended price (3:1) | $0.0625 | $0.25 |
| Cached input / 1M | — | — |
| Context window | 131K | 262K |
| Max output | 16K | 16K |
| Intelligence index | — | 4.4 |
| Coding index | 2.7 | 43.4 |
| Providers | — | — |
| Best provider uptime (30m) | — | — |
| Vision input | Yes | Yes |
| Reasoning | No | Yes |
| Tool calling | No | Yes |
| Released | 2025-03-13 | 2026-04-02 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Gemma 3 4B or Gemma 4 31B?
Gemma 3 4B is 4.0× cheaper than Gemma 4 31B on a typical 3:1 input/output mix.
Gemma 3 4B vs Gemma 4 31B: which has a bigger context window?
Gemma 3 4B: 131,072 tokens. Gemma 4 31B: 262,144 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Gemma 3 4B ≈ $150.00, Gemma 4 31B ≈ $600.00.
More comparisons
Gemma 3 4B vs Gemini 4 CarbonGemma 3 4B vs Claude Fable 5.2Gemma 3 4B vs Gemini Omni 1.2 FlashGemma 3 4B vs Gemini Omni 1.1 FlashGemma 3 4B vs Hy4Gemma 3 4B vs GLM 5.3 FlashX LegalGemma 3 4B vs GPT-6.1 TerraGemma 3 4B vs GPT-6.1 Terra ProGemma 3 4B vs Kimi K3.1 ProGemma 3 4B vs MiniMax M3.1 FlashGemma 3 4B vs DeepSeek V4.1 Flash 1017Gemma 3 4B vs Nemotron 3.5 Super VLGemma 3 4B vs Gemini 4 ArgonGemma 3 4B vs Claude Haiku 5.5Gemma 3 4B vs Nano Banana 2.1Gemma 3 4B vs Mistral Large 4Gemma 4 31B vs Gemini 4 CarbonGemma 4 31B vs Claude Fable 5.2Gemma 4 31B vs Gemini Omni 1.2 FlashGemma 4 31B vs Gemini Omni 1.1 FlashGemma 4 31B vs Hy4Gemma 4 31B vs GLM 5.3 FlashX LegalGemma 4 31B vs GPT-6.1 TerraGemma 4 31B vs GPT-6.1 Terra Pro