Integrations

VS Code

VS Code can use DEVUP AI models in chat and Agent mode through its built-in Custom Endpoint, with no extension required.

Prerequisites

VS Code
A DEVUP AI API key from https://devupai.com/dashboard/api-keys

Add DEVUP AI as a Custom Endpoint

Open Chat in VS Code.

Open the native Chat panel in VS Code.

Open the model picker above the chat input and choose Manage Models.

In the chat panel, click the active model name above the input area to reveal the dropdown and select Manage Models.

Choose Add Models, then Custom Endpoint.

From the management menu, select Add Models and pick Custom Endpoint.

For API Type, choose Chat Completions.

Select Chat Completions as the protocol format.

Give the group a name and enter your DEVUP AI API key when prompted.

Assign an identifier to your endpoint group and supply your API key from the API keys dashboard.

VS Code opens chatLanguageModels.json. Add your model inside the models array of the Custom Endpoint group.

Paste the following configuration inside the models array:

json

{
  "id": "deepseek-ai/DeepSeek-V4-Pro",
  "name": "DeepSeek V4 Pro (DEVUP AI)",
  "url": "https://api.devupai.com/v1/chat/completions",
  "toolCalling": true,
  "vision": false,
  "maxInputTokens": 1048576,
  "maxOutputTokens": 16000
}

•url is the full endpoint path, not a base URL.

•Set vision to match the model you are adding. Models without image input should have it set to false.

Save the file, then select the model in the chat model picker.

Save chatLanguageModels.json and pick your new model directly in the chat panel.

Select the model in the chat picker and send any message; the model responds in chat and works in Agent mode.

VS Code Language Models panel with DeepSeek V4 Pro (DEVUP AI) added under Custom Endpoint

chatLanguageModels.json entry

json

{
  "id": "deepseek-ai/DeepSeek-V4-Pro",
  "name": "DeepSeek V4 Pro (DEVUP AI)",
  "url": "https://api.devupai.com/v1/chat/completions",
  "toolCalling": true,
  "vision": false,
  "maxInputTokens": 1048576,
  "maxOutputTokens": 16000
}

chatLanguageModels.json Field Reference

Each entry in the Custom Endpoint models array accepts the following parameters:

Field	Type	Description
id	string	Model identifier from DEVUP AI catalog (e.g. "deepseek-ai/DeepSeek-V4-Pro")
name	string	Display label shown in VS Code model picker
url	string	Full endpoint path: "https://api.devupai.com/v1/chat/completions"
toolCalling	boolean	Set to true to enable workspace tool use and Agent mode
vision	boolean	Set to match model capabilities; false for models without image input
maxInputTokens	number	Input context window matching the model being added (verify model-specific limits in the models catalog)
maxOutputTokens	number	Maximum generation tokens matching the model being added (verify model-specific limits in the models catalog)

Use Agent mode

In Agent mode, VS Code reads workspace files, runs terminal commands, and applies code edits through tool calling, and streams the model's replies into the chat.

VS Code Agent mode creating and running hello.py with DeepSeek V4 Pro (DEVUP AI)

Choosing a model

For Agent mode, use a model whose catalog entry supports tool calling, for example deepseek-ai/DeepSeek-V4-Pro, and set toolCalling to true in its entry. See Tool Calling and Models.

Troubleshooting

Authentication error (401)enter your DEVUP AI key as-is when VS Code prompts for it.
Model IDthe id field must match the catalog exactly, for example deepseek-ai/DeepSeek-V4-Pro.

Vercel AI SDK

Zed