Head to head
Gemma 4 31B IT vs Gemma 4 31B Instruct (Pearl AI)
On a blended workload of one million input tokens and three million output tokens, Gemma 4 31B Instruct (Pearl AI) is 1.2× cheaper than Gemma 4 31B IT.
| Gemma 4 31B IT | Gemma 4 31B Instruct (Pearl AI) | |
|---|---|---|
| Provider | Together AI | Together AI |
| Input / MTok | $0.39 | $0.28 |
| Output / MTok | $0.97 | $0.86 |
| Cache read / MTok | — | — |
| Context window | 262,144 | 32,000 |
| Blended 1M in + 3M out | $3.30 | $2.86 |
| Status | ga | ga |
Gemma 4 31B IT detail Gemma 4 31B Instruct (Pearl AI) detail