Token Plan Overview
Download
フォーカスモード
フォントサイズ
Tencent Cloud Large Language Model Token Plan Personal Edition is a personal subscription plan designed for OpenClaw and coding scenarios, offering four tiers to choose from.
Plan Advantages
Switch seamlessly between multiple models on need: With a single subscription, you can freely switch among models such as MiniMax-M2.7, Kimi-K2.6, GLM-5.2, and DeepSeek-V4-Pro.
Compatible with popular OpenClaw and mainstream AI coding tools: The plan supports AI tools such as OpenClaw, Claude Code, OpenCode, Cline, Cursor, Kilo Code, and Codex CLI, with shared quota across toolsempowering OpenClaw to assist with coding anytime, anywhere, and enabling a more flexible AI coding experience.
Multiple tiers tailored to diverse scenarios: Lite, Standard, Pro, and Max tiers are available to support a wide range of needs, from first-time OpenClaw exploration to intensive coding workflows.
Monthly subscription for simplified management: Monthly subscription for simplified management: The monthly subscription model makes it easier to plan usage and manage your budget.
Getting Started
Users who are already familiar with the general Token Plan can follow the Token Plan Quick Start guide to get started quickly.
Plan Benefits
Plan Specifications
The plan uses a credit-based deduction model. For detailed deduction rules, see Token Plan Personal Edition Credit Deduction Rules. Plan usage is described as follows:
Note:
The Lite tier is intended for lightweight trial use only.
Plan | Lite Plan | Standard Plan | Pro Plan | Max Plan |
Price | USD 7/month | USD 17/month | USD 51/month | USD 103/month |
Usage Limit | Per subscription month 1000 credits | Per subscription month 2600 credits | Per subscription month 7900 credits | Per subscription month 15900 credits |
Recommended | Best for beginners and first-time exploration. Ideal for first-time users exploring OpenClaw capabilities, including web operations, file processing, data analysis, scheduled tasks, and more. | Great value for daily use. Suitable for daily office work and lightweight development with OpenClaw, including batch file processing, demo creation, automated workflows, and more. | High-f Designed for frequent AI development,with a token quota three times higher than the Standard plan. Ideal for developers and productivity-focused users who rely on AI heavily every day, supporting parallel work across multiple repositories, complex logic generation, code refactoring, agent orchestration, and more. | The preferred choice for intensive AI develoopment,with expanded quota support. Built for power users who use AI as a core productivity tool, supporting full-stack AI generation, multi-agent collaboration, CI automation, and more. |
Available models
All four tiers support the following models.
Note:
To continuously improve model service capabilities and user experience, the AI models included in the platform plans are provided as part of a dynamically updated model library. Models may be added, replaced, upgraded, adjusted in availability, or gradually discontinued based on factors such as model performance, service stability, compliance requirements, licensing status, and third-party model availability. The plans provide access to the corresponding models available in the platforms current model library, and do not constitute a commitment to the continuous, fixed, or permanent availability of any specific model.The models displayed at the time of subscription reflect availability at that point in time only. The actual available models, versions, and invocation scope are subject to the purchase page, console display, and platform announcements. For model discontinuations or major adjustments that may affect subscribed users, the platform will provide advance notice through reasonable means, such as announcements, in-site messages, or console notifications.
The Auto model is the systems intelligent routing model. It analyzes request content in real time and dynamically routes traffic to the most suitable underlying model based on task complexity, cost, and latency.
For DeepSeek V4 Flash and DeepSeek V4 Pro model services provided directly by DeepSeek, TokenHub does not provide SLA guarantees for these services. By using these models, you acknowledge and agree to comply with DeepSeek service agreement. Please carefully read the relevant terms before use. If you do not accept the above terms, please stop using these models immediately.
Model Name | Model ID | Model Capability | Length Limits (tokens) |
GLM-5.2 | glm-5.2 glm-5-2 | Deep reasoning, text generation | Context window: 1M Maximum input: 1M Maximum output: 128k |
Kimi-K2.6 | kimi-k2.6 kimi-k-2-6 | Deep reasoning, text generation, image understanding | Context window: 256k Maximum input: 256k Maximum output: 256k |
DeepSeek-V4-Pro (Vendor Direct) | deepseek-v4-pro-202606 | Deep reasoning, text generation | Context window: 1M Maximum input: 1M Maximum output: 384k |
DeepSeek-V4-Flash (Vendor Direct) | deepseek-v4-flash-202605 | Deep reasoning, text generation | Context window: 1M Maximum input: 1M Maximum output: 384k |
MiniMax-M3 | minimax-m3 | Deep reasoning, text generation | Context window: 1M Maximum input: 1M Maximum output: - |
| | | |
Auto model | auto | Deep reasoning, text generation | - |
Dedicated API Key
The Token Plan Personal Edition supports generating only one dedicated API Key (in the format sk-tp-xxxx). You can obtain the package's API Key from the Token Plan page. Other API Keys in TokenHub cannot be used with Token Plan.
Generate an API Key:
Copy the API Key:
Access URLs
The URL configured for each tool varies depending on the protocol it supports:
Protocol | Base URL | Full URL |
Tools compatible with the OpenAI API protocol. | https://tokenhub-intl.tencentcloudmaas.com/plan/v3 | https://tokenhub-intl.tencentcloudmaas.com/plan/v3/chat/completions |
Tools compatible with the Anthropic API protocol. | https://tokenhub-intl.tencentcloudmaas.com/plan/anthropic | https://tokenhub-intl.tencentcloudmaas.com/plan/anthropic/v1/messages |
Supported Region
Token Plan Personal Edition is available in the Singapore region.
Plan Validity Period
Token Plan is billed in calendar-month units, with the validity period starting from the date and time of successful purchase. Examples of a one-month plan validity period are as follows:
Purchase Date | Subscription Duration | End Date |
01.04 10:00:00 | 1 month | 02.04 9:59:59 |
01.31 10:00:00 | 1 month | 02.28 9:59:59 |
02.01 10:00:00 | 1 month | 03.01 9:59:59 |
Quota Refresh Rules
If the plan quota is exhausted within the current validity period, it will be automatically restored in the next cycle. No other resource packages or account balance will be consumed. For detailed deduction rules, see Token Plan Personal Edition Credit Deduction Rules.
Usage Restrictions
1. Subscription Account Policy: The account is for the exclusive use of the subscriber. Account sharing is strictly prohibited. If account sharing occurs, it may result in restricted subscription benefits. Tencent cannot guarantee your rights and interests. Please be aware of this.
2. API Calls Strictly Prohibited: They are permitted for use only within Supported AI Tools. It must not be used via API calls in automated scripts, custom application backends, or any non-interactive batch calling scenarios. Using the plan API Key for calls outside the permitted scope will be deemed a violation of the agreement between you and Tencent, and may result in suspension of the subscription or revocation of the API Key. Tencent assumes no liability for any service impairment caused by such violations.
3. Rate Limit: Concurrency limits are associated with your plan tier and may be dynamically adjusted by the platform based on resource availability. As a general rule, the concurrency priority is Max > Pro > Standard > Lite.
Subscription Rules
Purchase Restrictions
Each root account can purchase only one Token Plan at a time, regardless of whether it is Lite, Standard, Pro, or Max.If a root account has multiple sub-accounts, the root account and all of its sub-accounts can purchase only one plan in total and must share the plan quota.
Renewal Rules
Token Plan supports both manual renewal and automatic renewal. The detailed descriptions are as follows:
Manual Renewal: You can manually renew the plan at any time after purchase and before expiration.
On the Large Language Model Service Platform TokenHub > Token Plan page, click Renew Now to renew the plan.
Automatic Renewal: If you select automatic renewal when placing the order, the system will automatically deduct the fee for the next renewal cycle from your account's available balance before the plan expires, provided that the account has sufficient balance. If you did not select automatic renewal when placing the order, go to the large language model service platform TokenHub > Token Plan page, click Open to enable automatic renewal.
Note:
Automatic Renewal Rules
During automatic renewal, available vouchers will be used first. If needed, you can go to Voucher Management to disable automatic voucher usage.
Automatic renewal will fail under circumstances such as insufficient account balance, restrictions on new purchases for the account, or abnormal account real-name verification.
The price for automatic renewal may be affected by factors such as real-time pricing. The actual renewal price may differ from the currently displayed price. Please refer to the order price at the time the system actually performs the automatic renewal.
Warning:
Please renew your Token Plan before it expires. Once the plan has expired, it can no longer be renewed and will become invalid. Remaining Token quota cannot be carried over to the next month, and the API Key will also become invalid. Tools/applications/services using that API Key will immediately be unable to call the API.
Quota Activation Rules After Renewal:
Plan renewal refers to renewing the plan for the next subscription month. After renewal is completed, the new quota will take effect in the next subscription month:
If the quota for the current subscription month has not been used up: The remaining quota can continue to be used until the end of the current subscription month, and the quota will be automatically reset to the new amount in the next subscription month.
If the quota for the current subscription month are exhausted: renewal will not reset the quota for the current subscription month. The new quota will take effect only in the next subscription month.
Example: A user purchases a Standard plan, which includes 2,600 credits for the current subscription month (2026-06-23 to 2026-07-23). The user renews the plan for the next subscription month (2026-07-23 to 2026-08-23). The available quota under different scenarios is described as follows:
Scenario | Quota usage in the Current Subscription Month (2026-06-23–2026-07-23) | Remaining Available Quota in the Current Subscription Month (2026-06-23–2026-07-23) | Available Quota in the Next Subscription Month (2026-07-23–2026-08-23) |
Quota not fully used in the current subscription month | Assuming 1,000 credits have been used in the current subscription month | 1600 credits | 2600 credits |
Quota fully used in the current subscription month | Assuming 2,600 credits have been used in the current subscription month | 0 credits | 2600 credits |
Upgrade Rules
The plan validity period remains unchanged. You can upgrade your plan by paying the price difference. To upgrade,, on the Large Language Model Service Platform TokenHub > Token Plan page, click Upgrade to upgrade your package.
Upgrade fee = New plan price − Original plan price (price difference).
Plan credits after upgrade = Credits of the new plan − Credits already used under the original plan
Note:
Token Plan supports plan upgrades only, plan downgrades are not supported.
After the plan is successfully upgraded:
The plan API Key remains unchanged.
The expiration date remains the same as that of the original plan. For example, if a Lite plan expires on 2026-07-23, the upgraded Standard plan will also expire on 2026-07-23.
Unsubscription Rules
Once purchased, the plan cannot be canceled or refunded.
Supported AI Tools
Coding Tools | ||
An intelligent coding tool based on Tencent Cloud's AI technology | open-source AI coding agent tool | Lightweight High-performance coding tool |
VSCode extension, code completion, and debugging | AI-Native Code Editor | Lightweight High-performance coding tool command line |
AI Terminal Programming Assistant, supports natural language coding | Intelligent coding agent introduced by OpenAI | A development tool with deeply integrated AI capabilities |
FAQs
フィードバック