Continue with SeibertGPT

AI assistant as an extension for VS Code and JetBrains – chat and code changes right in the editor.

Intermediatetested with Continue 2.1.0 on September 28, 2026 · all tools

1. Prerequisites

You need a SeibertGPT plan and an API key. You get both after signing in.

2. Download for macOS

In VS Code, open Extensions (Cmd+Shift+X), search for “Continue” and install it.

3. Set up

Store the key

In the folder ~/.continue, create a file named .env with this line (your key instead of YOUR_KEY). Continue reads the key from there; the file is stored unencrypted on your computer.

Command

SEIBERTGPT_API_KEY=YOUR_KEY

Store the config file

Download config.yaml and put it in the same folder. If there's already a config.yaml there, copy over only the entries under “models”.

Choose the model

In the Continue chat, select the model “No thinking – fast (SeibertGPT)”.

File: ~/.continue/config.yaml · Download config.yaml

Important: if config.yaml already exists, don't replace it. The file also contains your other settings; copy over only our entries.

config.yaml

name: SeibertGPT
version: 1.0.0
schema: v1
models:
  - name: "Standard with thinking (SeibertGPT)"
    provider: openai
    model: "deepseek-v41-flash"
    apiBase: "https://api.seibert.ai/v1"
    apiKey: ${{ secrets.SEIBERTGPT_API_KEY }}
    capabilities: [tool_use, image_input]
    defaultCompletionOptions:
      contextLength: 1000000
  - name: "No thinking – fast (SeibertGPT)"
    provider: openai
    model: "deepseek-v41-flash-fast"
    apiBase: "https://api.seibert.ai/v1"
    apiKey: ${{ secrets.SEIBERTGPT_API_KEY }}
    capabilities: [tool_use, image_input]
    defaultCompletionOptions:
      contextLength: 1000000
  - name: "Low reasoning effort (SeibertGPT)"
    provider: openai
    model: "deepseek-v41-flash-low"
    apiBase: "https://api.seibert.ai/v1"
    apiKey: ${{ secrets.SEIBERTGPT_API_KEY }}
    capabilities: [tool_use, image_input]
    defaultCompletionOptions:
      contextLength: 1000000
  - name: "High reasoning effort (SeibertGPT)"
    provider: openai
    model: "deepseek-v41-flash-high"
    apiBase: "https://api.seibert.ai/v1"
    apiKey: ${{ secrets.SEIBERTGPT_API_KEY }}
    capabilities: [tool_use, image_input]
    defaultCompletionOptions:
      contextLength: 1000000
  - name: "Maximum reasoning effort (SeibertGPT)"
    provider: openai
    model: "deepseek-v41-flash-max"
    apiBase: "https://api.seibert.ai/v1"
    apiKey: ${{ secrets.SEIBERTGPT_API_KEY }}
    capabilities: [tool_use, image_input]
    defaultCompletionOptions:
      contextLength: 1000000

4. Test

Select a function in the editor and ask in the chat “What does this code do?” – Continue explains it.

5. Troubleshooting

Error 401

Continue can't find the key: the .env file must be in the .continue folder and contain the line SEIBERTGPT_API_KEY=… – then reload the editor.

HTTP 401 – key rejected

The key was copied incorrectly or has been revoked. Create a new key under Account → API keys.

HTTP 403 – IP binding

Your key is currently bound to a different IP (e.g. another device). Wait for the lock period to expire or release the binding under Account → API keys.

HTTP 413 – cold_request_too_large

A new or long-paused session starts with a lot of context. Start a new session or shorten the history.

“Hinweis von SeibertGPT: Der Kontext ist zu … gefüllt” (German context notice)

You're approaching your plan's context limit. Summarize the history (e.g. /compact) or start over.

Nothing works after an update

These tools change quickly. The version the guide was tested with is shown at the top – let us know if something no longer matches.