GPT-4o Image API
Native image generation inside GPT-4o — generate and edit images within the conversation.
curl -X POST https://runapi.ai/api/v1/gpt_4o_image/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-image",
"prompt": "Based on our conversation about the brand redesign, generate a mockup of the new homepage hero section."
}'import { Gpt4oImageClient } from "@runapi.ai/gpt-4o-image";
const client = new Gpt4oImageClient();
const result = await client.textToImage.run({
model: "gpt-4o-image",
prompt: "Based on our conversation about the brand redesign, generate a mockup of the new homepage hero section.",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\Gpt4oImage\Gpt4oImageClient;
$client = new Gpt4oImageClient();
$result = $client->textToImage->run([
'model' => 'gpt-4o-image',
'prompt' => 'Based on our conversation about the brand redesign, generate a mockup of the new homepage hero section.',
]);require "runapi/gpt_4o_image"
client = RunApi::Gpt4oImage::Client.new
result = client.text_to_image.run(
model: "gpt-4o-image",
prompt: "Based on our conversation about the brand redesign, generate a mockup of the new homepage hero section."
)npx skills add runapi-ai/gpt-4o-image -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 cursorGPT-4o Image enables native image generation directly within GPT-4o conversations, combining language understanding with visual creation in a single model. It interprets conversational context to produce contextually accurate images.
- 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
價格
技術細節
| Model ID | gpt-4o-image |
| 供應商 | OpenAI |
| 模態 | image |
| 任務類型 | asynchronous |
| 計費單位 | call |
| API endpoint | /api/v1/gpt_4o_image/text_to_image |
| 商用授權 | 是 — 已透過 API 包含 |
| 目錄狀態 | 可直接上線 |
為 app 開發安裝 GPT-4o Image 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-4o-image -gInstall the GPT-4o Image skill for this app: 1. Add runapi-ai/gpt-4o-image 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.
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。
什麼是 GPT-4o Image API？
GPT-4o Image integrates visual creation natively into GPT-4o, combining reasoning with generation. Through RunAPI, it shares the same API access and billing as all OpenAI models.
為什麼透過 RunAPI 使用 GPT-4o Image 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。
常見問題
What makes GPT-4o Image different from GPT Image?
GPT-4o Image generates images natively within the GPT-4o conversation, using conversational context to inform the image. GPT Image is a standalone generation endpoint.
How does conversational context help?
The model uses the full conversation history to understand what you want — you can iteratively refine images by describing changes in natural language.
How many objects can it handle in one image?
GPT-4o Image handles many distinct objects in a single scene while maintaining compositional coherence and object identity.
Can I edit a previously generated image?
Yes — describe the changes in the conversation and the model modifies the existing image while preserving the rest of the scene.
Is it good for iterative design workflows?
Yes — the conversational interface makes it natural to iterate: generate, review, describe adjustments, and regenerate without rewriting the full prompt.
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。
可以商業使用嗎？
可以——除非模型授權明確限制，否則每個版本都包含商業使用權；若有例外，會在版本頁面標示。
速率限制怎麼算？
每個金鑰的速率限制會依使用等級而提升。最新限制請參考定價頁面。
如果遇到問題，要去哪裡回報？
請在公開的 GitHub repo 開 issue，或寄信給支援。
如果你喜歡 GPT-4o Image API，可以試試這些
開始用 GPT-4o Image API 開發。
- text_to_image