Head to head
Gemma 4 31B Instruct (Pearl AI) vs GPT-4o mini
On a blended workload of one million input tokens and three million output tokens, GPT-4o mini is 1.5× cheaper than Gemma 4 31B Instruct (Pearl AI).
| Gemma 4 31B Instruct (Pearl AI) | GPT-4o mini | |
|---|---|---|
| Provider | Together AI | OpenAI |
| Input / MTok | $0.28 | $0.15 |
| Output / MTok | $0.86 | $0.6 |
| Cache read / MTok | — | $0.075 |
| Context window | 32,000 | 128,000 |
| Blended 1M in + 3M out | $2.86 | $1.95 |
| Status | ga | ga |