Skip to content

Subscription Plans

ZenMux Builder Plan subscriptions provide individual developers with a fixed monthly fee and a predictable way to use AI models—so you can focus on coding and creating without worrying about the cost of each API call.

What are Flows?

A Flow is the metering unit used in ZenMux subscriptions, combining both token usage and request count.

📖 What can the Pro plan ($20/month, 50 Flows/5h) actually do?

Use CaseExample ModelsUsage per 5 HoursMonthly Usage
Image generationNanoBananaPro, etc.2K resolution 16:9, ~30 images~2000 images
CodingClaude Sonnet 4.5, etc.Complete 5–10 coding tasks~500+ tasks
ChatGPT-5.2, etc.~200 conversations~12,000 chats

💡 Notes

  • Coding: Task complexity directly affects token consumption, which can cause significant differences in Flow usage.
  • Chat: Calculated based on 5000 input tokens + 1000 output tokens.
  • Different models can be converted proportionally based on unit pricing.

Why choose Builder Plan?

💡 Key Advantages

Pain PointSubscription Solution
Worried about burning money while vibe codingFixed pricing from $20/month—code freely
Learning new tech is too expensiveExplore a wide range of AI models at low cost
Messy multi-platform account managementOne API Key for all models
Diverse needsCoding + image generation + chat—full-scenario coverage

🚀 Three Core Values

  1. Full-scenario model coverage

    Builder Plan covers three major model categories. Whether you’re a developer, designer, PM, or operator, one subscription covers the full set of Vibe Builder use cases:

    Model TypeRepresentative Models
    Coding modelsClaude Opus 4.5 / GPT-5.2-Codex / Gemini-3-Pro-Preview ...
    Image modelsNanoBananaPro / GPT-Image-1.5 ... (rolling out)
    Text generationGPT-5.2 / Qwen3-Max-Thinking / ERNIE 5.0 ...
  2. An all-star model lineup

    One subscription lets you orchestrate the world’s top models (Gemini 2.5 Pro, GPT-5 series, Claude Opus/Sonnet 4 series, etc.). Get the latest flagship models as soon as they’re available—like having the strongest compute fleet working together.

  3. Seamless IDE compatibility

    No tool lock-in. One subscription API Key works across popular community developer tools like Claude Code, Cursor, CodeX, and more.

Plan Comparison

subscription-free

Free - Try for Free


subscription-free

Supported models:

  • deepseek/deepseek-chat - DeepSeek-V3.2 (Non-thinking Mode)
  • deepseek/deepseek-reasoner - DeepSeek-R1.8
  • inclusionai/ling-1t - inclusionAI: Ling-1T
  • inclusionai/ling-mini-2.0 - inclusionAI: Ling-Mini-2.0
  • inclusionai/ring-1t - inclusionAI: Ring-1T
  • inclusionai/ring-mini-2.0 - inclusionAI: Ring-Mini-2.0
  • minimax/minimax-m2.1 - MiniMax: MiniMax M2.1
  • stepfun/step-3 - StepFun: Step-3
  • volcengine/doubao-seed-1.8 - VolcanoEngine: Doubao-Seed-1.8
  • xiaomi/mimo-v2-flash - Xiaomi: MiMo-V2-Flash
  • z-ai/glm-4.6v-flash - Z.AI: GLM 4.6V Flash
  • z-ai/glm-4.7 - Z.AI: GLM 4.7

Pro - Best for Developers


subscription-free

Supported models: 70+ premium models, organized by provider below (modelSlug - description)


Anthropic Claude Series

  • anthropic/claude-opus-4.6 - Claude Opus 4.6
  • anthropic/claude-opus-4.5 - Claude Opus 4.5
  • anthropic/claude-sonnet-4.5 - Claude Sonnet 4.5
  • anthropic/claude-haiku-4.5 - Claude Haiku 4.5
  • anthropic/claude-opus-4.1 - Claude Opus 4.1
  • anthropic/claude-opus-4 - Claude Opus 4
  • anthropic/claude-3.5-sonnet - Claude 3.5 Sonnet
  • anthropic/claude-3.5-haiku - Claude 3.5 Haiku
  • anthropic/claude-3.7-sonnet - Claude 3.7 Sonnet
  • anthropic/claude-sonnet-4 - Claude Sonnet 4

OpenAI GPT Series

  • openai/gpt-5.2 - GPT‑5.2
  • openai/gpt-5.2-chat - GPT‑5.2 Chat
  • openai/gpt-5.2-codex - GPT‑5.2 Codex
  • openai/gpt-5 - GPT‑5
  • openai/gpt-5-chat - GPT‑5 Chat
  • openai/gpt-5-codex - GPT‑5 Codex
  • openai/gpt-5-mini - GPT‑5 Mini
  • openai/gpt-5-nano - GPT‑5 Nano
  • openai/gpt-5.1 - GPT‑5.1
  • openai/gpt-5.1-chat - GPT‑5.1 Chat
  • openai/gpt-5.1-codex - GPT‑5.1 Codex
  • openai/gpt-5.1-codex-mini - GPT‑5.1 Codex Mini
  • openai/gpt-4.1 - GPT‑4.1
  • openai/gpt-4.1-mini - GPT‑4.1 Mini
  • openai/gpt-4.1-nano - GPT‑4.1 Nano
  • openai/gpt-4o - GPT‑4o
  • openai/gpt-4o-mini - GPT‑4o Mini
  • openai/o4-mini - o4-mini

Google Gemini / Gemma Series

  • google/gemini-2.0-flash - Gemini 2.0 Flash
  • google/gemini-2.0-flash-lite-001 - Gemini 2.0 Flash Lite
  • google/gemini-2.5-flash - Gemini 2.5 Flash
  • google/gemini-2.5-flash-lite - Gemini 2.5 Flash Lite
  • google/gemini-2.5-flash-image - Gemini 2.5 Flash Image
  • google/gemini-2.5-pro - Gemini 2.5 Pro
  • google/gemini-3-flash-preview - Gemini 3 Flash Preview
  • google/gemini-3-pro-preview - Gemini 3 Pro Preview
  • google/gemini-3-pro-image-preview - Gemini 3 Pro Image Preview
  • google/gemma-3-12b-it - Gemma 3 12B IT

xAI Grok Series

  • x-ai/grok-4 - Grok 4
  • x-ai/grok-4-fast - Grok 4 Fast
  • x-ai/grok-4-fast-non-reasoning - Grok 4 Fast Non‑Reasoning
  • x-ai/grok-4.1-fast - Grok 4.1 Fast
  • x-ai/grok-4.1-fast-non-reasoning - Grok 4.1 Fast Non‑Reasoning
  • x-ai/grok-code-fast-1 - Grok Code Fast 1

Z.AI GLM Series

  • z-ai/glm-4.6v - GLM 4.6V
  • z-ai/glm-4.6v-flash - GLM 4.6V Flash
  • z-ai/glm-4.7 - GLM 4.7
  • z-ai/glm-4.5 - GLM 4.5
  • z-ai/glm-4.5-air - GLM 4.5 Air
  • z-ai/glm-4.6 - GLM 4.6

DeepSeek Series

  • deepseek/deepseek-chat - DeepSeek Chat
  • deepseek/deepseek-chat-v3.1 - DeepSeek Chat V3.1
  • deepseek/deepseek-v3.2 - DeepSeek V3.2
  • deepseek/deepseek-v3.2-exp - DeepSeek V3.2 Exp
  • deepseek/deepseek-r1-0528 - DeepSeek R1 0528
  • deepseek/deepseek-reasoner - DeepSeek Reasoner

Qwen / Tongyi Qwen Series

  • qwen/qwen3-coder - Qwen3 Coder
  • qwen/qwen3-coder-plus - Qwen3 Coder Plus
  • qwen/qwen3-max - Qwen3 Max
  • qwen/qwen3-max-preview - Qwen3 Max Preview
  • qwen/qwen3-vl-plus - Qwen3 VL Plus
  • qwen/qwen3-14b - Qwen3 14B
  • qwen/qwen3-235b-a22b-2507 - Qwen3 235B A22B 2507
  • qwen/qwen3-235b-a22b-thinking-2507 - Qwen3 235B A22B Thinking 2507

Moonshot / Kimi Series

  • moonshotai/kimi-k2.5 - Kimi K2.5
  • moonshotai/kimi-k2-thinking - Kimi K2 Thinking
  • moonshotai/kimi-k2-thinking-turbo - Kimi K2 Thinking Turbo
  • moonshotai/kimi-k2-0711 - Kimi K2 0711
  • moonshotai/kimi-k2-0905 - Kimi K2 0905

Baidu ERNIE Series

  • baidu/ernie-5.0-thinking-preview - ERNIE 5.0 Thinking Preview
  • baidu/ernie-x1.1-preview - ERNIE X1.1 Preview

InclusionAI Series

  • inclusionai/ling-1t - Ling‑1T
  • inclusionai/ling-flash-2.0 - Ling Flash 2.0
  • inclusionai/ling-mini-2.0 - Ling Mini 2.0
  • inclusionai/llada2.0-flash-cap - LLADA 2.0 Flash Cap
  • inclusionai/ming-flash-omni-preview - Ming Flash Omni Preview
  • inclusionai/ring-1t - Ring‑1T
  • inclusionai/ring-flash-2.0 - Ring Flash 2.0
  • inclusionai/ring-mini-2.0 - Ring Mini 2.0

Meta Llama Series

  • meta/llama-3.3-70b-instruct - Llama 3.3 70B Instruct
  • meta/llama-4-scout-17b-16e-instruct - Llama 4 Scout 17B 16E Instruct

Mistral Series

  • mistralai/mistral-large-2512 - Mistral Large 2512

MiniMax Series

  • minimax/minimax-m2-her - MiniMax M2 her
  • minimax/minimax-m2.1 - MiniMax M2.1
  • minimax/minimax-m2 - MiniMax M2

Kuaishou

  • kuaishou/kat-coder-pro-v1 - KAT‑Coder‑Pro‑V1

Stepfun

  • stepfun/step-3 - Step 3

Volcengine Doubao

  • volcengine/doubao-seed-1-6-vision - Doubao Seed 1.6 Vision
  • volcengine/doubao-seed-1.8 - Doubao Seed 1.8
  • volcengine/doubao-seed-code - Doubao Seed Code

Xiaomi

  • xiaomi/mimo-v2-flash - MiMo V2 Flash

Image Generation Models

  • nanobanana/nanobanana-pro - NanoBananaPro (2K resolution; supports 16:9 and more aspect ratios)
  • openai/gpt-image-1.5 - GPT-Image-1.5 (coming soon)
  • tencent/hunyuan-image3 - Hunyuan-Image3 (coming soon)

Max - High-Intensity Development


subscription-free

Additional top-tier flagship models:

  • openai/gpt-5.2-pro - GPT-5.2 Pro
  • openai/gpt-5-pro - GPT-5 Pro

Ultra - Professional Flagship


subscription-free

Supported models: Same as the Max plan, including all premium models and all top-tier flagship models.

Usage Limits

⚠️ Important

Subscription plans are designed for personal development, learning/exploration, vibe coding, and other non-production use cases. Please follow the usage rules below:

Rate Limits

  • Rate Limit: 10–15 RPM (requests per minute)
  • Quota window: Refreshed within a rolling 5-hour window
  • Weekly limit: Resets within a rolling weekly window

Applicable Scenarios

Allowed:

  • Personal development and learning
  • Vibe coding and rapid prototyping
  • Technical exploration and experimentation
  • Personal projects and non-commercial applications

Not allowed:

  • Production environments that are already live
  • Commercial products or services
  • End-user–facing applications
  • Abusive behavior such as pooling multiple accounts for round-robin usage

💡 Production recommendation

If your project is about to go live or is already commercialized, switch to the Pay-As-You-Go usage-based plan to get:

  • Higher SLA guarantees
  • More stable service quality
  • More flexible scalability
  • Professional commercial support

How to Subscribe

Step 1: Review plan details

Visit the ZenMux Pricing page to view detailed information and pricing for all subscription plans.

subscription-free

Step 2: Choose a plan and subscribe

  1. Select the plan that fits you on the Pricing page
  2. Click the corresponding "Get Max" or "Get Ultra" button (Pro users click "Upgrade")
  3. Complete the payment process

💡 Public beta capacity

Subscriptions are now available in public beta, with a total of 999 spots. Once spots are filled, new sign-ups will be temporarily closed—subscribe early to secure access.

Step 3: Manage your subscription and get an API Key

After subscribing, go to the Subscription management page:

subscription-free
  • 📊 View usage

    • Usage and remaining time in the current 5-hour window
    • Cumulative usage stats for the current week
    • Flow consumption breakdown
  • 🔑 Get a subscription API Key

    • Generate an API Key specifically for subscriptions
    • Manage and rotate existing keys
    • View the key’s last-used time
  • 💳 Manage subscription

    • View current plan information
    • Upgrade or downgrade your plan
    • View billing history

Extra Usage - Automatic Overages Fallback

When your subscription’s 5-hour window or weekly window quota is exhausted, Extra Usage can automatically switch to the Pay As You Go API Key you set, so you can continue seamlessly without being blocked by time-window limits. Once your subscription quota is restored, the system automatically switches back to subscription billing.

💡 Key Benefits

  • Seamless switching - Automatically switches to usage-based billing when quota runs out—no manual API Key changes
  • No workflow interruption - Does not affect your development, coding, or chat flows
  • Auto restore - Automatically switches back to subscription billing once your quota is restored
  • Flexible control - Enable or disable at any time

Setup Steps

Go to the Subscription management page and configure Extra Usage as follows:

Step 1: Enable Extra Usage

In the subscription management page, find the Extra Usage section and toggle the switch on the right to enable it.

Enable Extra Usage

Step 2: Select a Pay As You Go API Key

After toggling, a "Select a Key" dialog appears. You can:

  • Select an existing Pay As You Go API Key from the dropdown list
  • Or click "Create new key" to create a new usage-based API Key
Select API Key

After selecting, click "Select" to confirm.

Step 3: Done

After enabling, the page will show details for your selected Pay As You Go API Key, including:

  • API Key name and secret
  • Enablement status
  • Created time and last-used time
  • Current amount spent
  • Actions (you can reselect another key)
Extra Usage Enabled

How It Works

  1. Normal usage - Subscription quota (Flows) is used first
  2. Quota exhausted - When the 5-hour window or weekly window reaches its limit, automatically switch to the configured Pay As You Go API Key
  3. Usage-based billing - Calls are charged against your account balance
  4. Auto restore - When the subscription quota window resets, automatically switch back to subscription billing

💡 Recommendations

  • Make sure your Pay As You Go account has sufficient balance to avoid service interruption after fallback switching due to insufficient funds
  • You can view Extra Usage usage and spend at any time from the subscription management page
  • To change the backup key, just click "Reselect" and choose again

⚠️ Billing notice

After you enable Extra Usage, when your subscription quota is exhausted, charges will be automatically deducted from your Pay As You Go balance. Monitor your balance to avoid unexpected costs.

Step 4: Use it in developer tools

After you obtain your subscription API Key, you can use it in various developer tools and applications.

Same usage as Pay As You Go

Using a subscription API Key is exactly the same as Pay As You Go: it works with the OpenAI SDK, Anthropic SDK, and direct HTTP calls. The only difference is that you use a subscription-specific API Key (starting with sk-ss-v1-), and usage is deducted from your subscription quota instead of your balance.

💡 API call examples

For complete API call examples, see the Quickstart. Just replace the API Key in the examples with your subscription API Key.

Integrate with mainstream developer tools

Subscription API Keys integrate seamlessly with popular AI coding tools and apps. For detailed configuration steps, see:

🔧 AI Coding Tools

💬 Knowledge Management & Chat Tools

🤖 AI Application Platforms

📚 More integrations

More integration guides are continuously being added. If you need help, visit our Discord community or contact technical support.


Using Subscriptions in Studio Chat

In addition to using your API Key in developer tools, you can also use your subscription quota directly in ZenMux Studio Chat (web) for conversations.

Switch billing mode

Studio Chat billing mode switch

On the Studio Chat page, you can choose per conversation whether to use subscription quota or Pay As You Go balance.

As shown, you can find the Billing Mode option in conversation settings:

  • Subscription - Use subscription quota (Flows); does not consume account balance
  • Pay As You Go - Charges are deducted from your account balance based on actual usage

💡 Flexible switching

You can use different billing modes for different conversations. For example:

  • Daily development, learning, prototyping → use Subscription
  • Production testing, commercial validation → use Pay As You Go

You can switch between the two modes at any time. They don’t affect each other, so you can always pick the most suitable billing mode for each scenario.

⚠️ Shared quota

Studio Chat and API calls share the same subscription quota pool. Conversations in Studio Chat consume subscription Flows—plan your usage accordingly.


FAQ

What’s the difference between subscriptions and Pay As You Go?

FeatureSubscription (Builder Plan)Pay-As-You-Go
BillingFixed monthly feeBilled by actual usage
Best forPersonal dev, learningProduction, commercial apps
Cost predictability✅ High (fixed monthly)⚠️ Medium (varies with usage)
Rate limits10–15 RPMHigher; configurable
SLAStandardHigher
Price leverage✅ 5–10×Standard API pricing

When does quota reset?

  • 5-hour window: Uses a rolling window mechanism, metered from when the request is sent; resets every 5 hours
  • Weekly limit: Metered from when the request is sent; resets every 7 days

You can view remaining quota and reset times in real time on the Subscription management page.

Can I use multiple plans at the same time?

No. One account can have only one active subscription plan at a time. If you need higher limits, upgrade to the Max or Ultra plan.

Next Steps

Now that you understand how Builder Plan subscriptions work, you can:

  • 📚 Read the Quickstart to learn detailed API calling methods
  • 🔧 See Best Practices to integrate your subscription API Key into developer tools
  • 💰 Learn about Pay As You Go, the billing option for production
  • 📊 Visit Usage Analytics to monitor subscription quota usage in real time
  • 💵 Review Cost Analytics to learn how to optimize usage costs

Contact Us

If you encounter any issues while using the service, feel free to reach us via:

For more contact options and details, visit our Contact page.