Flux 2 API
Text-to-image and remix-image with strong prompt adherence from Black Forest Labs.
curl -X POST https://runapi.ai/api/v1/flux_2/remix_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-2-flex-text-to-image",
"prompt": "Generate a photorealistic studio portrait of an astronaut holding a cat, dramatic rim lighting, fine detail."
}'import { Flux2Client } from "@runapi.ai/flux-2";
const client = new Flux2Client();
const result = await client.remixImage.run({
model: "flux-2-flex-text-to-image",
prompt: "Generate a photorealistic studio portrait of an astronaut holding a cat, dramatic rim lighting, fine detail.",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\Flux2\Flux2Client;
$client = new Flux2Client();
$result = $client->remixImage->run([
'model' => 'flux-2-flex-text-to-image',
'prompt' => 'Generate a photorealistic studio portrait of an astronaut holding a cat, dramatic rim lighting, fine detail.',
]);require "runapi/flux_2"
client = RunApi::Flux2::Client.new
result = client.remix_image.run(
model: "flux-2-flex-text-to-image",
prompt: "Generate a photorealistic studio portrait of an astronaut holding a cat, dramatic rim lighting, fine detail."
)npx skills add runapi-ai/flux-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 cursorFlux 2 is Black Forest Labs' text-to-image and image remix model known for strong prompt adherence and high visual fidelity. Its pro tier auto-enhances prompts, while the flex tier exposes manual control over inference steps and guidance.
- 多個變體，對應不同速度／品質層級
- Model skill 包含文件、schema 與 setup 備註
- 支援 app-focused coding workflows
- 生成失敗不收費
比較所有 API 變體
為 app 開發安裝 Flux 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/flux-2 -gInstall the Flux 2 skill for this app: 1. Add runapi-ai/flux-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.
從 model skill 到第一次結果，只需四步
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。
Flux 2 API 是甚麼？
Flux 2 is Black Forest Labs' generation model, delivering high prompt adherence across text-to-image and remix-image tasks. Through RunAPI, Pro and Flex variants share the same API shape.
為何透過 RunAPI 使用 Flux 2 API
一個驗證，對應所有 provider
一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶，亦無需為每個整合輪換密鑰。
統一定價與計費
按次以 USD 收費，每月結算。失敗的生成不會收費。
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 is the difference between Pro and Flex?
Pro is the flagship tier with automatic prompt enhancement. Flex gives you control over inference steps and guidance, and supports up to 8 reference images.
How strong is prompt adherence?
Flux 2 is specifically known for strong prompt adherence — it follows detailed descriptions including spatial relationships, colors, and object counts more faithfully than most models.
Does Flux 2 support remix-image?
Yes — both Pro and Flex have dedicated remix-image variants that use source images as style or content seeds.
What is automatic prompt enhancement?
The Pro variant automatically refines your prompt for better visual results. This is a zero-config feature — no extra parameters needed.
How does Flux 2 compare to Flux Kontext?
Flux 2 is for generating new images from prompts or remixing source images. Flux Kontext is for editing existing images with contextual awareness.
我應該先用邊個版本？
先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本，之後再升級到 pro 用於正式生產。
有免費方案嗎？
新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。
你哋支援串流結果嗎？
如有提供串流，RunAPI 會端到端串流。
失敗會點樣收費？
生成失敗不會收費。
輸出有快取嗎？
已生成輸出會儲存，並可按任務 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，否則每個版本都包括商業使用。相關限制會在版本頁面列明。
限流點樣計？
每個密鑰的限流會跟使用等級而提升。最新限制請參考定價頁。
可以在邊度報告問題？
可以在公開 GitHub repo 開 issue，或者電郵支援。