VS Code Copilot Chat
VS Code chat adds FreeTheAI through its Custom Endpoint provider (bring your own key). It works even without a Copilot plan.
Category: Coding tools. Before you start, you need a FreeTheAI account, an API key, and today's check-in.
Settings
| Setting | Value |
|---|---|
| Provider | Custom Endpoint |
| API type | Chat Completions |
| url | https://api.freetheai.org/v1/chat/completions |
| API key | Your FreeTheAI key (ftai_..., 53 characters) |
Steps
Open the language models
In the chat model picker, press the gear (Manage Language Models), or run Chat: Manage Language Models.
Add a Custom Endpoint
Press Add Models, choose Custom Endpoint, enter a group name (FreeTheAI) and your key, and choose Chat Completions.
Describe the models
VS Code opens chatLanguageModels.json. Fill in the models and save:
[
{
"name": "FreeTheAI",
"vendor": "customendpoint",
"apiKey": "ftai_your_key_here",
"apiType": "chat-completions",
"models": [
{
"id": "fta/zai/glm-5.3",
"name": "GLM 5.3",
"url": "https://api.freetheai.org/v1/chat/completions",
"toolCalling": true,
"vision": false,
"maxInputTokens": 200000,
"maxOutputTokens": 32000
}
]
}
]Pick the model
Choose GLM 5.3 in the chat model picker. Restart VS Code if it does not show up.
Tips
- If VS Code already wrote an apiKey value (a reference to its secret storage), keep that line instead of pasting your key.
- Without a GitHub sign-in, set chat.utilityModel and chat.utilitySmallModel to a FreeTheAI model so titles and commit messages work.
- Bring your own key covers chat and agent mode, not inline code completions.
Common questions
I used the old "OpenAI Compatible" provider. Does it still work?
It is deprecated. Add FreeTheAI again with the Custom Endpoint provider and the chat-completions API type.
Why do I get a 401 "invalid API key" error?
The key is wrong or incomplete. Remove the FreeTheAI group, add it again, and paste the whole ftai_ key (53 characters).
The model does not show in the picker. What now?
Save chatLanguageModels.json and restart VS Code.
Agent mode does nothing with FreeTheAI. Why?
Keep "toolCalling": true and use a model that supports tools, such as fta/zai/glm-5.3 or fta/kimi/k3.
Why do I get a 403 error?
Free models need one check-in a day. Check in at freetheai.org/checkin, then try again.
More help
How this guide was checked
Checked against the VS Code language models docs (Custom Endpoint provider) on 2026-09-29.

