# Gemma 4 31B-it FP8 vs MiniMax M2.7 FP4

On provider list prices, Gemma 4 31B-it FP8 costs $0.39 per million input tokens against $0.30 for MiniMax M2.7 FP4: effectively level. Output is $0.97 against $1.20 (1.2x).

## Specifications

| | Gemma 4 31B-it FP8 | MiniMax M2.7 FP4 |
| --- | --- | --- |
| Lab | Google | MiniMaxAI |
| Access | Open weights | Open weights |
| Context window | 256K tokens | 192K tokens |
| List price, input | $0.39 / M tokens | $0.30 / M tokens |
| List price, output | $0.97 / M tokens | $1.20 / M tokens |
| Cached input | n/a | $0.06 / M tokens |
| License | Apache 2.0 | Not listed |
| Fine-tunable | Yes | Yes |

Specifications and provider list prices from the Allocate catalog, checked 2026-07-21.

## What the numbers say

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each. That workload costs $780 a month on MiniMax M2.7 FP4 and $807.50 on Gemma 4 31B-it FP8 at list: a gap of $27.50.

Gemma 4 31B-it FP8 reads 256K tokens per request against 192K for MiniMax M2.7 FP4, 1.3x the window. That decides which one can take whole documents without splitting them.

## Choose Gemma 4 31B-it FP8 for

- The longer context window (256K vs 192K tokens)
- Fine-tuning under a permissive license (Apache 2.0)

## Choose MiniMax M2.7 FP4 for

- The lower list price ($0.30 in / $1.20 out per M tokens)
- Published cached-input pricing ($0.06 per M tokens)

## Common questions

### Which is cheaper, Gemma 4 31B-it FP8 or MiniMax M2.7 FP4?

MiniMax M2.7 FP4, on this workload shape. At list prices it is $0.30/$1.20 per million tokens in and out against $0.39/$0.97 for Gemma 4 31B-it FP8. Billed on Allocate: $0.32/$1.28 against $0.42/$1.04.

### Which has the bigger context window?

Gemma 4 31B-it FP8: 262,144 tokens (256K) against 196,608 (192K) for MiniMax M2.7 FP4.

### Can I fine-tune Gemma 4 31B-it FP8 or MiniMax M2.7 FP4?

Both publish open weights (Gemma 4 31B-it FP8: Apache 2.0; MiniMax M2.7 FP4: Not listed), so both can be fine-tuned. On Allocate the trained weights stay inside your boundary and belong to you.

---

[HTML page](https://allocate.network/compare/google-gemma-4-31b-it-vs-minimaxai-minimax-m2-7) · [Gemma 4 31B-it FP8](https://allocate.network/models/google-gemma-4-31b-it.md) · [MiniMax M2.7 FP4](https://allocate.network/models/minimaxai-minimax-m2-7.md) · [Machine-readable catalog](https://allocate.network/catalog.json)