token.app › Compare › GPT-4.1 vs Gemma 4 31B
GPT-4.1 vs Gemma 4 31B
Gemma 4 31B leads on 2 of 2 shared benchmarks. Gemma 4 31B is 22× cheaper per token on a blended 3:1 basis. GPT-4.1 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-4.1 | Gemma 4 31B | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $2.00 | $0.100 |
| Output $/1M | $8.00 | $0.340 |
| Blended $/1M | $3.50 | $0.160 |
| Context window | 1.0M | 262K |
| Max output | 33K | 262K |
| Released | Apr 2025 | Apr 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 66.9% | 75.8% |
| OTIS Mock AIME | 38.3% | 73.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose GPT-4.1 if…
- Larger context window (1.0M)
Choose Gemma 4 31B if…
- Costs less per token — $0.160 vs $3.50 blended
- Higher GPQA Diamond (75.8% vs 66.9%)
- Higher OTIS Mock AIME (73.3% vs 38.3%)
- Open weights — self-hostable
- Newer model (released Apr 2026)
FAQ
Which is better, GPT-4.1 or Gemma 4 31B?
Across the 2 benchmarks both models have independently-run scores for, GPT-4.1 leads on 0 and Gemma 4 31B leads on 2. Benchmarks are one input — price and context window are on this page too.
Is GPT-4.1 cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.160 versus $3.50 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.100. Output alone: $8.00 vs $0.340.
What context windows do GPT-4.1 and Gemma 4 31B have?
GPT-4.1: 1,047,576 tokens. Gemma 4 31B: 262,144 tokens.
Who makes GPT-4.1 and Gemma 4 31B?
GPT-4.1 is made by OpenAI. Gemma 4 31B is made by Google.