Skip to main content

Large Model Access Guide

This document will guide you on how to access and configure various large models in the cloud development platform.

CloudBase has pre-integrated Hunyuan and DeepSeek into the platform.

Accessing Large Models

Precautions

Custom models only support large model interfaces compatible with the OpenAI protocol.

Required Parameters

Accessing a custom model requires the following three key parameters:

  • BaseURL: The request URL for the large model API (large model interface compatible with the OpenAI protocol)
  • APIKey: The access key for the large model API
  • Model name: The specific model identifier, such as hunyuan-turbos-latest, deepseek-chat, etc.

Access Steps

  1. Obtain BaseURL and API Key

The following provides access examples for hunyuan and DeepSeek. For other large models, please refer to the corresponding model provider's documentation.

ModelModel ProviderBaseURL ExampleModel NameBilling Information
hunyuanTencent Hunyuan Large Modelhttps://api.hunyuan.cloud.tencent.com/v1See Hunyuan Model ListSee Billing Documentation
DeepSeekTencent Cloud Agent Platform/DeepSeekhttps://api.lkeap.cloud.tencent.com/v1See DeepSeek Model ListSee Billing Documentation
DeepSeek only supports enabling postpaid
DeepSeekDeepSeek Officialhttps://api.deepseek.com/v1See DeepSeek Model ListSee DeepSeek Documentation
  1. Configure in the platform

    • Go to the CloudBase/AI+ console
    • Click "Add" or "Modify Configuration"
    Modify Configuration Entry
  2. Fill in BaseURL and API Key

The CloudBase platform has preconfigured the model names for Tencent Hunyuan Large Model and Tencent Cloud Agent Platform/DeepSeek.

If you need to access other large models, please fill in the corresponding model name in Model Name.

API Key Configuration Interface

Access Example

Official DeepSeek

  1. Obtain BaseURL and Model Name

    • Access the DeepSeek API Documentation

    • Confirm BaseURL: https://api.deepseek.com/v1

    • View available Model Name:

      • deepseek-chat (corresponds to DeepSeek-V3-0324)
      • deepseek-reasoner (corresponds to DeepSeek-R1-0528)
  2. Obtain API Key

  3. Configure on the CloudBase Platform

    • Go to the CloudBase/AI+ console

    • Click the "Create New Large Model" button

    • Enter the following information:

      • Group name (Custom)
      • BaseURL
      • API Key
      • Model name

  1. Wait for the configuration to take effect
    • The system requires a few minutes to complete the configuration.
    • After successful configuration, you will see the following effect:

Custom Model Configuration Succeeded

Frequently Asked Questions

Q: How to determine if my large model is compatible with the OpenAI protocol?

A: Large models compatible with the OpenAI protocol typically explicitly state this in their API documentation, or their API structure aligns with OpenAI's interface specifications (e.g., using similar endpoints and parameter structures).

Q: What should I do if the large model doesn't work properly after configuration?

A: Please check the following points:

  • Whether the API Key is correct and not expired
  • Is the BaseURL correct?
  • Whether the model name matches the provider's documentation
  • Is the network connection normal?