Head to head
Codestral 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 1.0× cheaper than Codestral.
| Codestral | Gemma 4 31B Instruct (Pearl AI) | |
|---|---|---|
| Provider | Mistral | Together AI |
| Input / MTok | $0.3 | $0.28 |
| Output / MTok | $0.9 | $0.86 |
| Cache read / MTok | — | — |
| Context window | — | 32,000 |
| Blended 1M in + 3M out | $3.00 | $2.86 |
| Status | ga | ga |