Image · OpenAI

GPT Image

Q: Do failed generations cost money?

失敗した生成は課金されません

Text-to-image and image editing powered by OpenAI's image generation models.

Operational · 2 endpoints · から $0.040

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/gpt-image -g

The -g flag installs globally so every project picks it up.

Or paste this prompt to your AI agent:

Install the GPT Image skill for me:

1. Clone https://github.com/runapi-ai/gpt-image
2. Copy the skills/gpt-image/ 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.

概要

GPT Image is OpenAI's image generation model supporting both text-to-image and image editing creation with strong compositional control. It produces high-quality visuals across photorealistic and stylized outputs.

Installable agent skill
Unified API key
SDK examples included
失敗した生成は課金されません

料金

失敗した生成は課金されません

Edit image

$0.04-$0.22 / image

Quality: high $0.22

Quality: medium $0.04

Text to image

$0.04-$0.22 / image

Quality: high $0.22

Quality: medium $0.04

仕様

Model ID	gpt-image-1.5
プロバイダー	OpenAI
モダリティ	image
Task type	asynchronous
課金	call
Endpoint	/api/v1/gpt_image/edit_image
Commercial	Yes
Status	Operational

AGENT USAGE

Use this model from your agent

Prompt + SDK example

# User prompt to the agent
"Generate a flat-design illustration of a team collaborating around a whiteboard, vibrant colors, clean lines."

// Code generated by the agent via @runapi.ai/gpt-image
import { GptImageClient } from '@runapi.ai/gpt-image';

const client = new GptImageClient();
const result = await client.editImage.run({
  model: 'gpt-image-1.5',
  prompt: 'Generate a flat-design illustration of a team collaborating around a whiteboard, vibrant colors, clean lines.',
});

@runapi.ai/gpt-image npm

仕組み

How to call this model

Install the skill

Add the model skill to your agent or install the SDK package.

Authenticate once

Use your RunAPI key for every supported model.

Send a request

Use the unified schema for the endpoint you need.

Receive output

Poll by task ID or handle the callback when the generation completes.

SDK QUICKSTART

SDK quickstart

runapi.ai

curl -X POST https://runapi.ai/api/v1/gpt_image/edit_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-image-1.5",
  "image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
  "prompt": "Generate a flat-design illustration of a team collaborating around a whiteboard, vibrant colors, clean lines."
}'

import { GptImageClient } from "@runapi.ai/gpt-image";

const client = new GptImageClient();
const result = await client.editImage.run({
    model: "gpt-image-1.5",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a flat-design illustration of a team collaborating around a whiteboard, vibrant colors, clean lines.",
});

require "runapi/gpt_image"

client = RunApi::GptImage::Client.new
result = client.edit_image.run(
    model: "gpt-image-1.5",
    image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
    prompt: "Generate a flat-design illustration of a team collaborating around a whiteboard, vibrant colors, clean lines."
)

@runapi.ai/gpt-image v1

背景

Where GPT Image fits

GPT Image is OpenAI's image generation model, supporting text-to-image and image editing. Through RunAPI, all GPT Image endpoints share one key and per-call pricing.

Provider

OpenAI

Modality

Image

RUNAPI を選ぶ理由