バリアント · Google / Imagen 4

Imagen 4 imagen-4-ultra API

A model variant exposed through RunAPI's unified AI API.

Operational · image · Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/imagen-4 -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the Imagen 4 skill for me:

1. Clone https://github.com/runapi-ai/imagen-4
2. Copy the skills/imagen-4/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
Switch variant
概要

Imagen 4 imagen-4-ultra is available through the same RunAPI auth, SDKs, and agent skill workflow.

  • Unified endpoint
  • SDK snippets
  • Agent install path
  • 失敗した生成は課金されません
料金

料金

失敗した生成は課金されません
Text to image
$0.12 / image
仕様

仕様

Model ID imagen-4-ultra
プロバイダー Google
モダリティ image
Task type asynchronous
課金 call
Endpoint /api/v1/imagen_4/text_to_image
Commercial Yes
Status Operational
クイックスタート

Quickstart — imagen-4-ultra

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": "Generate a product hero image of a matte-black water bottle on a beige stone surface, soft side light, 4K."
}'
import { Imagen4Client } from "@runapi.ai/imagen-4";

const client = new Imagen4Client();
const result = await client.textToImage.run({
    model: "imagen-4-ultra",
    prompt: "Generate a product hero image of a matte-black water bottle on a beige stone surface, soft side light, 4K.",
});
require "runapi/imagen_4"

client = RunApi::Imagen4::Client.new
result = client.text_to_image.run(
    model: "imagen-4-ultra",
    prompt: "Generate a product hero image of a matte-black water bottle on a beige stone surface, soft side light, 4K."
)
@runapi.ai/imagen-4 v1
仕組み

How to use imagen-4-ultra

01

Choose endpoint

Pick the endpoint and copy the SDK snippet.

02

Pass model ID

Use this variant ID in the request body.

03

Run task

Submit the request and store the returned task ID.

04

Collect output

Poll or receive the callback when the task finishes.

違い

How imagen-4-ultra compares

VS IMAGEN-4

Maximum photorealism and prompt adherence; brand/marketing grade

Balanced quality and speed; recommended default

VS IMAGEN-4-FAST

Maximum photorealism and prompt adherence; brand/marketing grade

~2.7s generation; rapid iteration and drafts

VS IMAGEN-4-PRO-REMIX-IMAGE

Maximum photorealism and prompt adherence; brand/marketing grade

Prompt-guided remix variant; source images to styled output

ユースケース

Where to use this variant

Image generation

Create visual assets from text prompts.

Editing

Transform existing images with prompt guidance.

Batch creative work

Use SDKs for repeatable generation.

FAQ

Frequently asked questions about imagen-4-ultra

How do I select imagen-4-ultra?

Pass the model ID shown in the quickstart.

Is pricing usage-based?

Yes. Pricing is metered per call or unit.

今すぐ開始

Start with Imagen 4 today.