# Gemma 4 31B 价格与规格

来源: https://modelbank.ai/zh/models/gemma-4-31b-it · 更新 2026-11-12 · ModelBank

| 项目 | 数值 |
|---|---|
| 厂商 | Google |
| 输入价格 | $0.2 / 1M tokens |
| 输出价格 | $0.4 / 1M tokens |
| 缓存输入 | n/a / 1M tokens |
| 上下文 | 262,144 tokens |
| 最大输出 | 16,384 tokens |
| 输入模态 | image,text,video |
| 推理 / 工具调用 | yes / yes |
| 智能指数 / 编码指数 | 4.4 / 43.4 |
| 发布 | 2026-04-02 |
| 下线日期 | 未公布 |

## 简介

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

## 价格历史

- 2026-09-24: $0.09 in / $0.34 out
- 2026-10-14: $0.2 in / $0.4 out
- 2026-10-26: $0.1 in / $0.34 out
- 2026-10-26: $0.2 in / $0.4 out

## 同等智能、更便宜的替代

- [GLM 5.3 Flash](https://modelbank.ai/zh/models/glm-5.3-flash): $0.0399 / $0.0784, intelligence 27.8
- [Granite 4.2 8B](https://modelbank.ai/zh/models/granite-4.2-8b): $0.06 / $0.15, intelligence 5.1
- [Nemotron 3.5 Lightning](https://modelbank.ai/zh/models/nemotron-3.5-lightning): $0.07 / $0.2, intelligence 5.5
- [DeepSeek V4.1 Flash 1017](https://modelbank.ai/zh/models/deepseek-v4.1-flash-1017): $0.098 / $0.29, intelligence 28.6
- [MiMo-V2.6-Flash](https://modelbank.ai/zh/models/mimo-v2.6-flash): $0.14 / $0.28, intelligence 26.7

JSON: https://modelbank.ai/api/v1/models/gemma-4-31b-it