Image · Black Forest Labs

Flux Kontext API

Flux Kontext API 调用上下文感知图像编辑，支持局部修改、风格迁移和角色一致性生成。

运行中 · 2 variants · 起价 $0.050

runapi.ai

curl -X POST https://runapi.ai/api/v1/flux_kontext/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "flux-kontext-max",
  "prompt": "编辑这张产品照片：将背景换成热带海滩，保持产品完全不变。"
}'

import { FluxKontextClient } from "@runapi.ai/flux-kontext";

const client = new FluxKontextClient();
const result = await client.textToImage.run({
    model: "flux-kontext-max",
    prompt: "编辑这张产品照片：将背景换成热带海滩，保持产品完全不变。",
});

<?php

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

use RunApi\FluxKontext\FluxKontextClient;

$client = new FluxKontextClient();
$result = $client->textToImage->run([
        'model' => 'flux-kontext-max',
        'prompt' => '编辑这张产品照片：将背景换成热带海滩，保持产品完全不变。',
]);

require "runapi/flux_kontext"

client = RunApi::FluxKontext::Client.new
result = client.text_to_image.run(
    model: "flux-kontext-max",
    prompt: "编辑这张产品照片：将背景换成热带海滩，保持产品完全不变。"
)

npx skills add runapi-ai/flux-kontext -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/flux-kontext v1

概览

Flux Kontext 是 Black Forest Labs 的上下文图像编辑模型，可在保留风格、角色特征和场景构图的同时进行精准编辑，擅长风格迁移和多次生成的视觉一致性保持。

多变体覆盖不同速度/质量层级
Model skill 包含文档、schema 和接入说明
适合面向应用的编码工作流
失败的生成不计费

变体

对比全部 API 变体

Variant	Billing	From
flux-kontext-max	call	$0.100	查看 →
flux-kontext-pro	call	$0.050	查看 →

技能

为应用开发安装 Flux Kontext skill

把模型文档、schema、定价说明和接入步骤加载进代码工作区。

# Install the model skill for app development workflows
npx skills add runapi-ai/flux-kontext -g

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

Or use this setup request in your coding tool:

Install the Flux Kontext skill for this app:

1. Add runapi-ai/flux-kontext 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.

OpenClaw