tencent cloud

Enterprise Token Plan Quick Start

Download
Modo Foco
Tamanho da Fonte
Última atualização: 2026-07-23 15:36:37
This document describes how to purchase an Enterprise Token Plan, create an API Key and quickly verify model calls, as well as how to use it in AI Agent or programming tools.

Step 1: Purchasing an Enterprise Token Plan Package

1. Log in to the TokenHub large language model service platform console, navigate to the Enterprise Token Plan purchase page, and select a subscription plan that suits your needs.
2. Configure the following plan parameters based on the type of plan you have purchased.
2.1 If you want to purchase a Pro Plan:
Configuration Item
Required or Not
Description
Example
Monthly Budget
Yes
Supports custom point specifications. Final prices and rules are subject to the console.
100,000 points
Package name.
Yes
Customize the plan name for easy identification and management (such as "R&D Team Plan" and "Product Line A Plan").
R&D Team Package
Purchase Duration
Yes
Select from 1 to 12 months.
1 month
Auto-renewal
No
Enable as needed. After enabling, the fee for the next month's package will be automatically deducted upon package expiration.
No
2.2 If you want to purchase a Lite Plan:
Configuration Item
Required or Not
Description
Example
Monthly Token quota
Yes
Supports custom specifications. Final prices and rules are subject to the console.
50,000,000 tokens
Package name.
Yes
Customize the plan name for easy identification and management (such as "R&D Team Plan" and "Product Line A Plan").
R&D Team Package
Purchase Duration
Yes
Select from 1 to 12 months.
1 month
Auto-renewal
No
Enable as needed. After enabling, the fee for the next month's package will be automatically deducted upon package expiration.
No
3. Confirm the configuration details and total cost, select the service terms, and click Buy Now to complete the payment.

Step 2: Obtaining an API Key

After purchasing a plan, you need to create and copy an API Key to obtain model call credentials.
1. In the My Plans list, choose a plan > Manage API Key to go to the API Key Management page.

2. Click Create API Key.
3. Fill in the API Key configuration and click Confirm to generate the API Key.
Field
Required or Not
Description
Example
Reuse Existing Key
No
Select an existing Key under the current plan from the dropdown list. Once selected, its configuration (model selection, dedicated quota, total quota limit, TPM restrictions) is automatically populated into the form below, facilitating the quick creation of a new Key with the same configuration. The Key name is not populated and must be re-entered.
If you select "Do Not Reuse", the configuration starts from scratch.
Do not reuse.
Key Name
Yes
Assign a custom name to the Key for easy identification of its purpose and ownership (for example, "Employee001", "Support Bot").
Naming rules: Can only contain Chinese characters, letters, digits, underscores, and hyphens. Must start with a Chinese character or letter and end with a Chinese character, letter, or digit. Length must be between 2 and 50 characters.
Employee001
Number of Keys to Create
Yes
The number of Keys to be created in this operation, ranging from 1 to -10. The system automatically appends a sequence number to the Key name (for example, "Employee001-1", "Employee001-2"). When Keys are created in batches, all Keys share the same configuration parameters.
1
Model Selection
Yes
Select the models that this Key can call. Multiple selections are supported. Available models include Auto Intelligent Routing, GLM-5, Kimi-K2.5, and MiniMax-M2.5.
If a model is not selected, an unauthorized error will be returned when the Key calls it.
Auto Intelligent Routing
Dedicated Quota
Yes
The dedicated quota reserved for this Key (unit: points/tokens) can only be used by this Key and cannot be occupied by other Keys. Setting it to 0 means no dedicated quota is reserved, and this Key only uses the shared pool. The input value must not exceed the currently allocatable dedicated quota (the page will prompt "Current maximum configurable X quota").
0
Total Quota Limit
Yes
The maximum total quota (sum of dedicated + shared portions) that this Key can use within the current billing cycle. Two modes are provided:
Same Plan Limit (Default): The limit equals the plan's total quota. This means the Key can theoretically use the entire quota pool, though actual usage is subject to competition within the shared pool.
Custom Limit: Manually enter a specific value to limit the Key's maximum available quota. This is suitable for scenarios that require strict control over the cost of a single Key.
Same as the package limit
TPM Limit
Yes
The maximum number of tokens that this Key can process per minute (Tokens Per Minute), used to control the call rate and prevent a single Key from excessively occupying bandwidth. Two modes are provided:
Same Plan Limit (Default): The TPM limit aligns with the plan level.
Custom Limit: Manually enter a value, which must not exceed the plan-level TPM limit.
Same as the package limit
4. Click Copy for an existing API Key to obtain the API Key.


Step 3: Quickly Validating Model Calls

After obtaining the API Key, you can use cURL in the command-line terminal to simply verify connectivity:
Replace $your_api_key with the API Key you created and copied in the previous step.
Replace $model_id with the model ID you want to test. The list of available models varies by plan. For details, see models available for the Pro Plan and models available for the Lite Plan. For example, auto.
The verification example is as follows:
Guangzhou
Singapore
curl --location 'https://tokenhub.tencentcloudmaas.com/plan/v3/chat/completions' \\
--header 'Authorization: Bearer $your_api_key' \\
--header 'Content-Type: application/json' \\
--data '{
"model": "$model_id",
"messages": [
{
"role": "user",
"content": "Write a poem about spring"
}
],
"stream": false
}'
Example Response
{
"id": "********-****-****-****-************",
"object": "chat.completion",
"model": "auto",
"created": *******,
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "**Spring Stroll**\\n\\nA gentle spring breeze caresses the face, willow catkins drift lightly,\\nPeach blossoms pink and plum blossoms white reflect in the lake's shimmer.\\nEmerald grass like mist carpets the narrow path,\\nSwallows dance, bees hum under the bright, clear sun.\\nKingfishers chirp on branches, their songs soft and fine,\\nClear springs mirror starlight upon the stones.\\nAll things awaken, singing of a prosperous age,\\nIn the human world, April is filled with fragrant blooms.",
"reasoning_content": "The user is speaking \\"Write a poem about spring\\". So we need to comply, providing a poem about spring ...."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 46,
"completion_tokens": 813,
"total_tokens": 859,
"prompt_tokens_details": {
"cached_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 748
}
}
}
curl --location 'https://tokenhub-intl.tencentcloudmaas.com/plan/v3/chat/completions' \\
--header 'Authorization: Bearer $your_api_key' \\
--header 'Content-Type: application/json' \\
--data '{
"model": "$model_id",
"messages": [
{
"role": "user",
"content": "Write a poem about spring"
}
],
"stream": false
}'
Example Response
{
"id": "********-****-****-****-************",
"object": "chat.completion",
"model": "auto",
"created": *******,
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "**Spring Stroll**\\n\\nA gentle spring breeze caresses the face, willow catkins drift lightly,\\nPeach blossoms pink and plum blossoms white reflect in the lake's shimmer.\\nEmerald grass like mist carpets the narrow path,\\nSwallows dance, bees hum under the bright, clear sun.\\nKingfishers chirp on branches, their songs soft and fine,\\nClear springs mirror starlight upon the stones.\\nAll things awaken, singing of a prosperous age,\\nIn the human world, April is filled with fragrant blooms.",
"reasoning_content": "The user is speaking \\"Write a poem about spring\\". So we need to comply, providing a poem about spring ...."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 46,
"completion_tokens": 813,
"total_tokens": 859,
"prompt_tokens_details": {
"cached_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 748
}
}
}

Step 4: Configuring AI Tools

The Token Plan Enterprise Plan is compatible with popular Lobster tools and AI coding tools. You can choose based on your preference, configure the URL, API Key, and specific model into the tool, and then use the large model service.
Openclaw Tools
OpenClaw
Open-source, self-hosted personal AI assistant
WorkBuddy
Tencent Cloud All-Scenario AI Desktop Agent
CoPaw
Open-source AI agent
AutoClaw
Local AI agent
QClaw
Tencent PC Manager Localized AI Assistant
Ongoing integration
Coding Tools
CodeBuddy
An intelligent coding tool based on Tencent Cloud AI technology
OpenCode
Open-source AI coding agent tool
Kilo Code
Lightweight High-performance coding tool
Cline
VSCode extension, code completion and debugging
Cursor
AI-native code editor
Kilo CLI
Lightweight High-performance coding tool command line
AI Terminal Programming Assistant, supports natural language coding
Codex
Intelligent coding agent introduced by OpenAI
Ongoing integration

More Operations

For API Key management, usage queries, plan upgrades, renewals, and more, see the Operation Guide.


Ajuda e Suporte

Esta página foi útil?

comentários