文档Docs
用火山方舟 Coding PlanUse a Volcano Ark Coding Plan
在中国大陆用字节跳动的火山方舟 Coding Plan 驱动 Agent J：先买 Lite，key 贴进手机密钥卡，用 OpenCode 或 Claude Code，默认豆包 Seed 2.1 Pro 能看截图。Run Agent J in mainland China on ByteDance's Volcano Ark Coding Plan: start with Lite, paste the key into the phone key card, use OpenCode or Claude Code; the default Doubao Seed 2.1 Pro reads screenshots.
火山方舟是字节跳动（抖音、豆包同一家）旗下火山引擎的模型平台。Coding Plan 是它专为编程工具推出的包月套餐，一把 key 就能调用豆包、Kimi、智谱 GLM、DeepSeek、MiniMax 这五家的 16 个模型。
还没决定用哪家？先看按你用的模型选。安装、配对手机这些每家都一样的事，看安装和手机上怎么用。
适合谁
- 在中国大陆，Claude Code 和 Codex 用不了，三家都还没有：我们首推它，先买 Lite。
- 已经开通了方舟 Coding Plan：直接用，不用再买别的。
- 在香港或海外：方舟的海外版叫 BytePlus，模型比大陆版旧、没有 Kimi K3，Agent J 也还没有它的一键配置。海外建议用 Kimi。
开通与套餐
- 打开火山方舟 Coding Plan 的官方活动页 https://www.volcengine.com/activity/codingplan ，用手机号注册火山引擎，完成实名认证。
- 订阅 Coding Plan，先买 Lite。Lite 和 Pro 能用的模型和工具完全一样（包括 Kimi K3），Pro 只是用量是 Lite 的 5 倍。额度不够再升级。
价格以下单页为准，见火山方舟 Coding Plan 活动说明。2026-10-16 我们核对时，新用户头两个月有活动价，活动到 2026-11-08。Lite 是入门档，Pro 用量是 Lite 的 5 倍，价格也更高。用量怎么算，见官方 Coding Plan 常见问题。
拿 key
- 打开方舟控制台 https://console.volcengine.com/ark/ ，在 API Key 管理里新建一把 key。
- 先别复制给任何人。 等手机上弹出密钥卡再贴。
把 key 交给 Agent J
跟电脑上的 Agent 说一句：帮我接上火山方舟 Coding Plan。它会这样做：
- 运行下面这条，把套餐里的 16 个模型写进 OpenCode 的设置。你原来的设置一项都不动。
agentj provider ark- 运行它打印出来的那条密钥卡命令。手机上会弹出密钥卡，名称是
ARK_CODING_PLAN_API_KEY，你只需把 key 贴进卡里。 - 重启后台服务，再切到方舟的默认模型：
agentj service restartagentj agent switch opencode --model ark-coding-plan/doubao-seed-2.1-pro方舟没有只读的核对接口，贴完 key 不能马上验。切过去以后的第一条回复就是核对：问它一句“你是哪个模型”，答出豆包就对了。
密钥卡怎么用，见手机上录入密钥。
能用的 AI 编程工具
方舟没有自带的编程命令行工具，用下面两个之一：
- OpenCode（默认）：上面那几步就是。没装 OpenCode 的，见装好 AI 命令行工具。
- Claude Code：你本来就习惯 Claude Code 时用。让 Agent 运行下面这条，它会打印三步，照着顺序做：存一份方舟的配置、弹密钥卡、启用这份配置。最后一步会先真发一句测试，通过了才改设置。
技术细节：接 Claude Code 的那条命令
agentj provider ark --harness claudeAgent J 会把 Claude Code 的 Haiku、Sonnet、Opus 和子 Agent 都指向同一个方舟模型，这样后台任务就不会因为向方舟请求 Claude 的模型名而失败。
模型与看图
| 用途 | 模型 | 能看截图 |
|---|---|---|
| 默认，日常加截图 | doubao-seed-2.1-pro | 能（实测） |
| 最强，但扣额度快 | kimi-k3 | 能（实测） |
| 便宜、快，也能看图 | deepseek-v4-1-flash | 能（实测） |
| 纯文本写代码 | glm-5.3、deepseek-v4-pro、deepseek-v4-flash | 不能 |
“实测”指 2026-10-16 我们在电脑上发一张软件截图，让模型读出弹窗标题、错误码、按钮上的字和表格里的金额，全部读对。手机上发 /model 能看到全部模型。Agent J 写进 OpenCode 的设置里，只给确认能看图的模型打开了图片输入，没确认的一律按纯文本处理。
用纯文本模型时，你从手机发截图、或者浏览器自动化要看页面，模型都看不到，会说没收到图片。这时换回 doubao-seed-2.1-pro 就行。
常见坑
- 报 401 或 403：多半是 key 贴错了，或者套餐还没开通。去控制台重新建一把，再弹一次密钥卡。
- Kimi K3 很快就用完了：方舟官方说它扣额度快，建议 Pro 用户用。Lite 也能选，用完前换回豆包就行。
- 提示另外计费：用错了地址。Agent J 写的是套餐专用的地址，不要自己手改。
- Coding Plan 不能生图：套餐里没有生图模型。
- 定时任务、客服 bot：这个套餐只给你在编程工具里交互用。没人看着的活要用按量付费的方舟 key，Agent J 不会把 Coding Plan 的 key 交给它们。
切回原来的工具
随时跟 Agent 说“切回 Claude Code”（或 Codex），它会先检查、能用才切。也可以自己在电脑上运行：
agentj agent switch claude想原样换回上一次切走前的那个：
agentj agent switch --undo切换的细节见换 AI 编程工具。
技术细节：地址和名字
- OpenCode 里的服务商名是
ark-coding-plan，模型写成ark-coding-plan/<模型>。 - OpenAI 兼容地址：
https://ark.cn-beijing.volces.com/api/coding/v3；Claude Code 用的 Anthropic 兼容地址：https://ark.cn-beijing.volces.com/api/coding/v1。这两个都是套餐专用地址。 - key 的环境变量名：OpenCode 用
ARK_CODING_PLAN_API_KEY；Claude Code 那份配置有自己的私有 key 文件，位置由 Agent J 打印的第二步给出。
Volcano Ark is the model platform on ByteDance's Volcano Engine cloud (the company behind Douyin and Doubao). Its Coding Plan is a monthly plan for coding tools: one key opens 16 models from five vendors, Doubao, Kimi, Zhipu GLM, DeepSeek and MiniMax.
Not sure which vendor to pick? Start at Choose by your model. Installing and pairing your phone are the same for every vendor: see Install and Using it on your phone.
Who it is for
- Mainland China, Claude Code and Codex not available, none of the three plans yet: our first recommendation; start with Lite.
- You already have an Ark Coding Plan: use it; there is nothing else to buy.
- Hong Kong or abroad: Ark's overseas edition, BytePlus, has older models and no Kimi K3, and Agent J has no one-step setup for it yet. Abroad we suggest Kimi.
Sign up and pick a plan
- Open the official Coding Plan page https://www.volcengine.com/activity/codingplan , sign up to Volcano Engine with your phone number and complete identity verification.
- Subscribe to the Coding Plan, Lite to start. Lite and Pro have exactly the same models and tools (Kimi K3 included); Pro only gives five times Lite's usage. Upgrade when you run short.
The order page is authoritative for prices: Coding Plan promotion. When we checked on 2026-10-16, new subscribers paid a promotional price for the first two months, until 2026-11-08. Lite is the entry plan; Pro has 5 times the usage of Lite and costs more. How usage is counted: the official Coding Plan FAQ.
Get the key
- Open the Ark console https://console.volcengine.com/ark/ and create a key under API Key management.
- Do not copy it to anyone yet. Wait for the key card on your phone and paste it there.
Hand the key to Agent J
Tell the Agent on your computer: connect my Volcano Ark Coding Plan. It will:
- Run this to add the plan's 16 models to OpenCode's settings. Nothing you already set is changed.
agentj provider ark- Run the key card command it prints. A key card named
ARK_CODING_PLAN_API_KEYopens on your phone; paste the key there and nowhere else. - Restart the background service, then switch to Ark's default model:
agentj service restartagentj agent switch opencode --model ark-coding-plan/doubao-seed-2.1-proArk has no read-only check, so the key cannot be tested the moment you paste it. The first reply after switching is the check: ask which model it is; Doubao means it works.
How the key card works: Admin rights and API keys, from your phone.
AI coding tools
Ark has no coding command-line tool of its own. Use one of these two:
- OpenCode (the default): the steps above. OpenCode not installed yet? See Set up AI command-line tools.
- Claude Code: if Claude Code is what you are used to. Ask the Agent to run the line below; it prints three steps to run in order: save an Ark profile, open the key card, use the profile. The last step sends one real test message and changes the settings only if it works.
Technical details: the Claude Code command
agentj provider ark --harness claudeAgent J points Claude Code's Haiku, Sonnet and Opus models and its subagent model at the same Ark model, so background work never asks Ark for a Claude model name and fails.
Models and screenshots
| Use | Model | Reads screenshots |
|---|---|---|
| Default, everyday work and screenshots | doubao-seed-2.1-pro | Yes (tested) |
| Strongest, but uses quota fast | kimi-k3 | Yes (tested) |
| Cheaper, fast, reads images too | deepseek-v4-1-flash | Yes (tested) |
| Text-only coding | glm-5.3, deepseek-v4-pro, deepseek-v4-flash | No |
Tested means: on 2026-10-16 we sent a software screenshot and asked the model for the dialog title, the error code, the button text and an amount in a table; it got all of them right. Send /model on your phone to see every model. In the OpenCode settings Agent J writes, image input is on only for models confirmed to read images; the rest are treated as text only.
With a text-only model, a screenshot from your phone or a page the browser automation needs to look at never reaches the model, and it says it got no image. Switch back to doubao-seed-2.1-pro.
Common problems
- 401 or 403: usually a mistyped key, or the plan is not active yet. Create a new key in the console and open the key card again.
- Kimi K3 runs out quickly: Ark says it uses quota fast and recommends it to Pro users. Lite can choose it too; switch back to Doubao before you run out.
- A message about separate billing: the wrong address is in use. Agent J writes the plan's own address; do not change it by hand.
- No image generation: the Coding Plan has no image-generation model.
- Scheduled tasks, support bots: the plan is for you, working interactively in a coding tool. Unattended work needs a pay-as-you-go Ark key; Agent J never hands the Coding Plan key to them.
Switch back
Tell the Agent at any time: switch back to Claude Code (or Codex). It checks first and switches only if that works. Or run it on the computer yourself:
agentj agent switch claudeTo go straight back to the tool you used before the last switch:
agentj agent switch --undoDetails: Switch AI coding tool.
Technical details: addresses and names
- In OpenCode the provider is
ark-coding-plan; models are writtenark-coding-plan/<model>. - OpenAI-compatible address:
https://ark.cn-beijing.volces.com/api/coding/v3; the Anthropic-compatible address Claude Code uses:https://ark.cn-beijing.volces.com/api/coding/v1. Both are the plan's own addresses. - Key variable: OpenCode reads
ARK_CODING_PLAN_API_KEY; the Claude Code profile keeps its own private key file, whose location Agent J prints in step two.