Google

Gemma 4 12B

开放权重apache-2.0发布于 2026年6月

Google's medium-size open-weight model with 12 billion parameters from the Gemma 4 family. Encoder-free unified multimodal architecture that natively processes text, image, audio, and video inputs without dedicated encoders. Features a 256K context window and supports 140+ languages. First medium-sized model capable of natively ingesting audio. Suitable for local deployment on GPUs with 16GB VRAM.

能力

对话文本补全视觉音频代码生成推理函数调用

模态

textimageaudiovideocode

上下文窗口

262K tokens

提供商

可用

由 3 家提供商提供

价格最低

Google AI Studio

$0.00/1M tokens

Google AI Studio, Hugging Face Inference, NVIDIA NIM

提供商（3）

按每百万输入与输出 token 的总成本排序。选择一行可查看提供商详情。

提供商	价格（每百万）	速率限制	区域	状态	延迟
Google AI Studio	输入: 免费输出: 免费	15 RPM / 500K TPM	us-east-1eu-west-1global	正常	0ms
NVIDIA NIM	输入: 免费输出: 免费	200 RPM / 500K TPM	us-east-1us-west-2	正常	0ms
Hugging Face Inference	输入: $0.10输出: $0.10	300 RPM / 500K TPM	us-east-1eu-west-1	正常	0ms

快速开始

通过 Google AI Studio 使用此模型，兼容 OpenAI SDK。

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.google-ai-studio.com/v1",
  apiKey: process.env.GOOGLE_AI_STUDIO_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gemma-4-12b-it",
  messages: [
    { role: "user", content: "Hello!" }
  ],
});

console.log(response.choices[0].message.content);

使用 Google AI Studio API · 兼容 OpenAI SDK