An API for everyoneUser guide
Website ↗
User guideTool setup

Connect DeepSeek Harness

Already have DeepSeek Harness installed? Follow the screenshots to connect your API, choose a model and thinking level, receive a first reply, and try a tool.

Set up the connection, step by step

The screenshots show the Chinese interface. Connection names and addresses are marked as teaching examples; keys are hidden. My API is a name you can choose yourself. API Base URL is a placeholder: replace it with the real address supplied by the platform.

01Open settings

  1. Click Settings (设置) at the bottom left

    Expand the sidebar from the top left if it is collapsed.

Open settings
Chinese interface · Open full-size screenshot

02Add a custom provider

  1. Open Models (模型)

    Select it in the settings sidebar.

  2. Add the provider

    Click Add custom provider (添加自定义提供方) near the bottom right.

Add a custom provider
Chinese interface · Open full-size screenshot

03Fill in the connection details

  1. Names

    You can use my-api for Provider ID and My API for the display name. They help you recognize this connection and do not have to match the platform brand.

  2. API address

    Paste the complete, current API address from the platform. Do not substitute the homepage address or copy the placeholder in the screenshot.

  3. API format

    Choose OpenAI Chat Completions, shown as openai-completions in this version.

  4. API key

    Paste your complete platform key without extra spaces.

  5. Fetch available models

    After filling in the four fields above, click 获取可用模型. Let the app fetch the list before choosing a model.

Fill in the connection details
Chinese interface · Open full-size screenshot

04Select a model and add it

  1. Check the returned list

    Our test returned deepseek-v4.1-flash-1017 and glm-5.2. Your available list may differ.

  2. Choose DeepSeek for this example

    All models may be selected initially. Keep DeepSeek and deselect glm-5.2 for this walkthrough.

  3. Click Add selected (添加所选)

    The chosen model returns to the connection form. This is the button label in the tested version.

Select a model and add it
Chinese interface · Open full-size screenshot

05Create and save the provider

  1. Check that the model was added

    The DeepSeek model you selected should appear below.

  2. Click Create provider (创建提供方)

    Use the button at the bottom of the form. Continue once your chosen name, My API in this example, appears in the provider list.

Create and save the provider
Chinese interface · Open full-size screenshot

06Enable thinking levels for the model

  1. Open the configuration file

    This version has no graphical switch for effort levels. Click 打开配置文件 at the top right of settings and open settings.yaml in a text editor.

  2. Find the model you just added

    Under your My API provider, find deepseek-v4.1-flash-1017 and add reasoningEfforts as shown below. Do not edit a model with the same ID under another provider.

  3. Save and check the menu

    Save, then reopen the model menu. Restart Harness if it has not updated. If your version has Model options → Reasoning levels, you can configure the levels there.

Enable thinking levels for the model
Chinese interface · Open full-size screenshot

Add reasoningEfforts only within the model entry you just created. Keep the existing address, credential reference, and other settings. This is a partial example: do not replace the whole file with it.

models:
  - id: deepseek-v4.1-flash-1017
    reasoningEfforts:
      low: low
      high: high
      max: max

Leading spaces matter. Indent with spaces and keep low, high, and max spelled exactly as shown.

07Choose a workspace

  1. Select a folder first

    If the input asks you to choose a workspace (选择工作区), use Add workspace (添加工作区). Select a folder you allow the app to work in; an empty practice folder is a good start.

  2. Check the folder name

    The screenshot uses harness-api-practice. You can choose another name. Continue when the folder name is visible.

Choose a workspace
Chinese interface · Open full-size screenshot

08Choose the model under My API

  1. Open the model menu

    Click the current model name at the bottom right of the message box, then open Models (模型).

  2. Choose your configured model

    Find the My API group and select deepseek-v4.1-flash-1017. It may display a custom name such as DeepSeek Flash.

Choose the model under My API
Chinese interface · Open full-size screenshot

09Choose the thinking level

  1. Open the model menu again

    With the My API model selected, click its name at the bottom right and open Reasoning levels (推理等级).

  2. Choose Low, High, or Max

    Start with High for everyday tasks; try Max for harder tasks and compare the results and usage on your own work.

  3. Check the selected level

    After choosing High, High appears beside the model name. DeepSeek Flash in the image is a display name for the same model.

Choose the thinking level
Chinese interface · Open full-size screenshot
After you select High, the level appears beside the model name.

After you select High, the level appears beside the model name.

Displaying the menu and upstream handling of each level are separate checks. Tested Off, Low, High, and Max requests were accepted; the Off sample returned no reasoning usage. Higher levels may take longer and use more tokens, without guaranteeing a better answer.

10Send your first message

  1. Check the model

    The bottom right should show the DeepSeek model you selected under My API.

  2. Send the test message below

    Copy the text below and click the send arrow. Sending uses billable model usage. Wait for the reply.

Send your first message
Chinese interface · Open full-size screenshot
Reply only: Connection successful. Do not use any tools or perform any other tasks.

11Receive a reply: the connection works

  1. Check the answer

    The test screenshot shows 连接成功。, meaning “Connection successful.” A matching text reply confirms that this chat request worked.

  2. Check usage

    Open Usage history on the platform to see the model usage. Next, try the file-reading task below.

Receive a reply: the connection works
Chinese interface · Open full-size screenshot