Head to head
Gemma 4 31B IT vs GPT-5.6 Luna
On a blended workload of one million input tokens and three million output tokens, Gemma 4 31B IT is 1.2× cheaper than GPT-5.6 Luna.
| Gemma 4 31B IT | GPT-5.6 Luna | |
|---|---|---|
| Provider | Together AI | OpenAI |
| Input / MTok | $0.39 | $0.2 |
| Output / MTok | $0.97 | $1.2 |
| Cache read / MTok | — | $0.02 |
| Context window | 262,144 | — |
| Blended 1M in + 3M out | $3.30 | $3.80 |
| Status | ga | ga |