Image · Google

Imagen 4 API

Imagen 4 API 调用照片级真实感文生图，精准排版渲染，广泛风格支持，最高 2K 分辨率。

运行中 · 4 variants · 起价 $0.040

runapi.ai

curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "imagen-4-ultra",
  "prompt": "生成一张产品主图：磨砂黑水壶放在米色石面上，柔和侧光，2K 分辨率。"
}'

import { Imagen4Client } from "@runapi.ai/imagen-4";

const client = new Imagen4Client();
const result = await client.textToImage.run({
    model: "imagen-4-ultra",
    prompt: "生成一张产品主图：磨砂黑水壶放在米色石面上，柔和侧光，2K 分辨率。",
});

<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\Imagen4\Imagen4Client;

$client = new Imagen4Client();
$result = $client->textToImage->run([
        'model' => 'imagen-4-ultra',
        'prompt' => '生成一张产品主图：磨砂黑水壶放在米色石面上，柔和侧光，2K 分辨率。',
]);

require "runapi/imagen_4"

client = RunApi::Imagen4::Client.new
result = client.text_to_image.run(
    model: "imagen-4-ultra",
    prompt: "生成一张产品主图：磨砂黑水壶放在米色石面上，柔和侧光，2K 分辨率。"
)

npx skills add runapi-ai/imagen-4 -g

# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor

@runapi.ai/imagen-4 v1

概览

Imagen 4 是 Google 的写实图像生成模型，支持精准排版渲染和最高 2K 分辨率输出，生成色彩准确、光照逼真的高细节图像。

多变体覆盖不同速度/质量层级
Model skill 包含文档、schema 和接入说明
适合面向应用的编码工作流
失败的生成不计费

变体

对比全部 API 变体

Variant	Billing	Pricing
imagen-4	call	$0.080	查看 →
imagen-4-fast	call	$0.040	查看 →
imagen-4-pro-remix-image	call	$0.240	查看 →
imagen-4-ultra	call	$0.120	查看 →

技能

为应用开发安装 Imagen 4 skill

把模型文档、schema、定价说明和接入步骤加载进代码工作区。

# Install the model skill for app development workflows
npx skills add runapi-ai/imagen-4 -g

Installs docs, schemas, pricing context, and setup notes into your developer workspace.

Or use this setup request in your coding tool:

Install the Imagen 4 skill for this app:

1. Add runapi-ai/imagen-4 with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.

OpenClaw