tencent cloud

LLM Service TokenHub

ドキュメントLLM Service TokenHubAPI Integration GuideAPI Usage Instructions

API Usage Instructions

Download
フォーカスモード
フォントサイズ
最終更新日: 2026-08-28 15:02:06
AI翻訳

Overview

The large model service platform TokenHub is compatible with OpenAI API and Anthropic API protocols, allowing direct use of the OpenAI SDK for quick access.

API domain name

For different regions, the platform provides different access addresses to offer you the most stable access. The default access addresses are as follows:
Site
API address
Resource Scheduling Scope
Singapore
https://tokenhub-intl.tencentcloudmaas.com
Global
Guangzhou
https://tokenhub.tencentcloudmaas.com
Chinese mainland
Silicon Valley
https://tokenhub-us.tencentcloudmaas.com
United States
The platform also provides backup access addresses to ensure users can access the service seamlessly in abnormal situations. When the default address is unavailable, you can try switching to the following access addresses:
Site
API address
Singapore
https://tokenhub-intl.tencentcloudmaas.tech
Guangzhou
https://tokenhub.tencentcloudmaas.tech
Silicon Valley
https://tokenhub-us.tencentcloudmaas.tech

Authentication method

Use the API KEY for authentication via the Authorization: Bearer Header.

Querying the Model List

You can query the range of models currently supported by the platform via the GET /v1/models API. This API is compatible with the OpenAI API protocol and returns a complete list of all models currently available for invocation on the platform, along with their status. The model ID is the value that needs to be passed to the model parameter when the inference API is called.
Attention:
To call the /v1/models API, you must include the API KEY in the request header for authentication (Authorization: Bearer <API KEY>). If authentication information is missing or the API KEY is invalid, the API returns an HTTP 401 error.

Request Example

curl https://tokenhub.tencentcloudmaas.com/v1/models \\
  -H "Authorization: Bearer $TOKENHUB_API_KEY"

Response Example

{
    "object": "list",
    "data": [
        {
            "id": "hy3",
            "object": "model",
            "name": "Hy3",
            "created": 1783267200,
            "status": "online"
        },
        {
            "id": "deepseek-v4-pro",
            "object": "model",
            "name": "DeepSeek-V4-Pro",
            "created": 1776960000,
            "status": "online"
        }
    ]
}

Response Parameter Description

Parameter
Type
Description
object
String
Fixed to list, indicating that the response is a list of models.
data
Array
An array of model objects, where each element represents an available model.
data[].id
String
The model ID. Pass this value to the model parameter when calling the inference API.
data[].object
String
The object type, fixed to model.
data[].name
String
The display name of the model.
data[].created
Integer
The model creation time (Unix timestamp, in seconds).
data[].status
String
The model status, such as online (online) and pre-offline (scheduled for decommission).

Model invocation method

Model Name
Model (API Parameter)
API Usage Guide
Hy4 preview
hy4-preview
For detailed API usage and parameters, refer to Language Model API Overview.
Hy3
hy3
DeepSeek-V4-Flash 0731 GA (Vendor Direct)
deepseek-v4-flash-202605
deepseek/deepseek-v4-flash-0731
deepseek/deepseek-v4-flash
DeepSeek-V4-Pro 0813 GA (Vendor Direct)
deepseek-v4-pro-202606
deepseek/deepseek-v4-pro-0813
deepseek/deepseek-v4-pro
DeepSeek-V4-Flash-Vision-Exp (Vendor Direct)
deepseek/deepseek-v4-flash-vision-exp
DeepSeek-V4-Flash 0731 GA
deepseek-v4-flash-0731
DeepSeek-V4-Pro 0813 GA
deepseek-v4-pro-0813
DeepSeek-V4-Flash
deepseek-v4-flash
DeepSeek-V4-Pro
deepseek-v4-pro
Deepseek-v3.2
deepseek-v3.2
GLM-5.3
glm-5.3
GLM-5.3-Flash
glm-5.3-flash
GLM-5.2
glm-5.2
GLM-5.1
glm-5.1
GLM-5
glm-5
GLM-5V-Turbo
glm-5v-turbo
GLM-5-Turbo
glm-5-turbo
Kimi K3
kimi-k3
Kimi K2.7 Code HighSpeed
kimi-k2.7-code-highspeed
Kimi K2.7 Code
kimi-k2.7-code
Kimi-K2.6
kimi-k2.6
Kimi-K2.5
kimi-k2.5
MiniMax-M3
minimax-m3
MiniMax-M2.7
minimax-m2.7
MiniMax-M2.5
minimax-m2.5
Hy-MT2-Plus
hy-mt2-plus
Kinfra-Text-Embedding-0.6b
kinfra-text-embedding-0.6b
For detailed API usage and parameters, refer to Embedding Model.
Kinfra-Text-Embedding-4b
kinfra-text-embedding-4b
Kinfra-VL-Embedding-2b
kinfra-vl-embedding-2b
Kinfra-VL-Embedding-8b
kinfra-vl-embedding-8b

Exception Handling

For API errors, see the API Error Codes section.



前の記事へ: Token Plan FAQs次の記事へ: Language Model API Overview

ヘルプとサポート

この記事はお役に立ちましたか？

フィードバック