Connect GitHub Copilot to LLMEasy with a custom model

​

Prerequisites

• Latest VS Code installed
• GitHub Copilot / Copilot Chat installed and signed in
• LLMEasy API Key ready (register and get one)
• The API Key belongs to the GPT group
• A model ID is available, for example gpt-5.5

​

Setup steps

1

Open model management

In the Copilot Chat input area, click the model selector, then choose Manage Models….

2

Add Custom Endpoint

In Language Models, click Add Models, then choose Custom Endpoint.

3

Enter the group name

In Group Name, enter:

LLMEasy

Then press Enter.

4

Enter the API Key

VS Code will ask for the API Key. Paste your LLMEasy API Key, then press Enter.This value will not be shown directly in the configuration file. VS Code stores it as a local secret and generates a reference like this:

"apiKey": "${input:chat.lm.secret.xxxxx}"

Do not replace ${input:chat.lm.secret...} with your real API Key. Keep the secret reference generated by VS Code.

5

Select the API type

In Custom Endpoint: API Type, select Chat Completions.

6

Edit the JSON configuration

VS Code opens chatLanguageModels.json. Confirm or update the configuration:

[
  {
    "name": "LLMEasy",
    "vendor": "customendpoint",
    "apiKey": "${input:chat.lm.secret.xxxxx}",
    "apiType": "chat-completions",
    "models": [
      {
        "id": "gpt-5.5",
        "name": "gpt-5.5",
        "url": "https://www.llmeasy.ru/v1/chat/completions",
        "toolCalling": true,
        "vision": true,
        "maxInputTokens": 1000000,
        "maxOutputTokens": 64000
      }
    ]
  }
]

Check these fields:

Field	Recommended value
name	LLMEasy
apiType	chat-completions
id	gpt-5.5 or another GPT group model ID from the model plaza
name	Same as the model ID
url	https://www.llmeasy.ru/v1/chat/completions
toolCalling	true
vision	true
maxInputTokens	1000000
maxOutputTokens	64000

7

Save and reload VS Code

Save chatLanguageModels.json, then run:

Developer: Reload Window

After reload, return to the Copilot Chat model selector and choose gpt-5.5.

8

Send a test message

Send a simple message in Copilot Chat:

Describe the model you are using in one sentence.

If Copilot Chat replies normally, the LLMEasy Custom Endpoint is configured successfully.

​

FAQ

​

Why should I enter the API Key in the prompt?

​

Why use Chat Completions?

https://www.llmeasy.ru/v1/chat/completions

​

Does this replace GitHub Copilot inline completion?

​

What should I do if I see Invalid token?

1. The API Key was entered in the VS Code prompt
2. JSON keeps the ${input:chat.lm.secret...} reference
3. The API Key belongs to the GPT group
4. url is https://www.llmeasy.ru/v1/chat/completions
5. apiType is chat-completions
6. The model ID is a GPT group model from the model plaza