Image · OpenAI

GPT Image 2

Q: Do failed generations cost money?

失敗した生成は課金されません

Latest OpenAI image generation with near-perfect multilingual text rendering inside images.

Operational · 2 endpoints · から $0.060

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/gpt-image-2 -g

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

Or paste this prompt to your AI agent:

Install the GPT Image 2 skill for me:

1. Clone https://github.com/runapi-ai/gpt-image-2
2. Copy the skills/gpt-image-2/ 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 2 is OpenAI's latest image generation model featuring near-perfect multilingual text rendering within generated images. It improves on instruction following and fine-grained visual detail over its predecessor.

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

Text to image

$0.06-$0.16 / image

Output resolution: 1k $0.06

Output resolution: 2k $0.10

Output resolution: 4k $0.16

Edit image

$0.06-$0.16 / image

Output resolution: 1k $0.06

Output resolution: 2k $0.10

Output resolution: 4k $0.16

仕様

Model ID	gpt-image-2
プロバイダー	OpenAI
モダリティ	image
Task type	asynchronous
課金	call
Endpoint	/api/v1/gpt_image_2/text_to_image
Commercial	Yes
Status	Operational

AGENT USAGE

Use this model from your agent

Prompt + SDK example

# User prompt to the agent
"Generate a greeting card with '新年快乐 Happy New Year' in decorative calligraphy, gold and red theme."

// Code generated by the agent via @runapi.ai/gpt-image-2
import { GptImage2Client } from '@runapi.ai/gpt-image-2';

const client = new GptImage2Client();
const result = await client.textToImage.run({
  model: 'gpt-image-2',
  prompt: 'Generate a greeting card with '新年快乐 Happy New Year' in decorative calligraphy, gold and red theme.',
});

@runapi.ai/gpt-image-2 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_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-image-2",
  "prompt": "Generate a greeting card with '新年快乐 Happy New Year' in decorative calligraphy, gold and red theme."
}'

import { GptImage2Client } from "@runapi.ai/gpt-image-2";

const client = new GptImage2Client();
const result = await client.textToImage.run({
    model: "gpt-image-2",
    prompt: "Generate a greeting card with '新年快乐 Happy New Year' in decorative calligraphy, gold and red theme.",
});

require "runapi/gpt_image_2"

client = RunApi::GptImage2::Client.new
result = client.text_to_image.run(
    model: "gpt-image-2",
    prompt: "Generate a greeting card with '新年快乐 Happy New Year' in decorative calligraphy, gold and red theme."
)

@runapi.ai/gpt-image-2 v1

背景

Where GPT Image 2 fits

GPT Image 2 is OpenAI's newest image model, notable for near-perfect multilingual text rendering. Through RunAPI, both text-to-image and image editing endpoints share one key.

Provider

OpenAI

Modality

Image

RUNAPI を選ぶ理由