Image · OpenAI

GPT Image 2 API

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

可直接上線 · 2 endpoints · 起價 $0.060

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.",
});

<?php

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

use RunApi\GptImage2\GptImage2Client;

$client = new GptImage2Client();
$result = $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."
)

npx skills add runapi-ai/gpt-image-2 -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/gpt-image-2 v1

OVERVIEW

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.

多種變體可對應不同速度／品質等級
Model skill 包含文件、schema 與 setup 備註
支援 app-focused coding workflows
生成失敗不收費

PRICING

價格

失敗的生成不收費

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

$0.16 / image

規格表

技術細節

Model ID	gpt-image-2
供應商	OpenAI
模態	image
任務類型	asynchronous
計費單位	call
API endpoint	/api/v1/gpt_image_2/text_to_image
商用授權	是 — 已透過 API 包含
目錄狀態	可直接上線

SKILLS

為 app 開發安裝 GPT Image 2 skill

將模型文件、schema、價格備註與 setup 步驟載入 coding workspace。

# Install the model skill for app development workflows
npx skills add runapi-ai/gpt-image-2 -g

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

Or use this setup request in your coding tool:

Install the GPT Image 2 skill for this app:

1. Add runapi-ai/gpt-image-2 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.

運作方式

從 model skill 到第一次結果，只要四步

選擇模型

挑選符合輸出類型、品質門檻與延遲目標的模型與變體。

設定

設定 RunAPI key，並在 coding workspace 安裝 model skill。

開發

使用 skill 指引，在你的 app 內加入模型功能。

接收

透過 task ID 查詢、在支援時串流，或處理 webhook callback。

CONTEXT

什麼是 GPT Image 2 API？

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

為什麼選 RunAPI

為什麼透過 RunAPI 使用 GPT Image 2 API

一組驗證，全部供應商通用

一把 RunAPI 金鑰就能開通整個目錄。無需分開註冊帳戶，也不用為每個整合各自輪替金鑰。

統一價格與計費

以美元按次計費，每月結帳。失敗的生成不收費。

內含 schema 的 skill

型別化 schema 與 setup 備註打包在 model skill 內，讓實作從正確契約開始。

FAQ

常見問題

How accurate is the multilingual text rendering?

GPT Image 2 可渲染多種語言的文字 — 英文和拉丁字母準確率約 99%，中文、日文、韓文和阿拉伯文等非拉丁文字約 95% 以上。

What is the maximum output resolution?

Up to 4K resolution (in beta); standard output is 2K. Both text-to-image and image editing endpoints support high-resolution output.

What is Thinking mode for image generation?

Thinking mode lets the model reason about composition and layout before generating, improving accuracy for complex multi-element scenes and precise text placement.

How does GPT Image 2 handle text in non-Latin scripts?

It renders CJK characters, Arabic, Cyrillic, and other scripts with near-native accuracy — a significant improvement over prior image generation models.

Can I generate and edit in the same workflow?

Yes — generate from text, then refine with image editing. Both endpoints share the same API shape.

我應該先從哪個版本開始？

先選擇符合你品質標準中最便宜的版本。大多數團隊會先用快速版本，之後再升級到專業版用於正式上線。

有免費方案嗎？

新帳戶可在每個模型上免費使用首次呼叫。之後則按次計費。

你們支援串流結果嗎？

只要該功能可用，RunAPI 會提供端到端串流。

失敗的請求如何計費？

生成失敗不會收費。

輸出結果有快取嗎？

生成結果會儲存，並可透過任務 ID 取回。輸入內容不會快取。