Connect → Continue

Use AxForge with Continue

Continue is an open-source assistant for VS Code: chat, edits and an agent mode. It takes any OpenAI-compatible service as a model in its config.yaml, with the key kept in a separate file.

Set it up

1. Open the configs

   Open Continue from its icon in the side bar. Click Main Config above the message box, then the gear beside Configs.

   

2. Open config.yaml

   On the Configs page, press the gear on Main Config. Continue opens its config.yaml in the editor.

   

3. Add the models

   Make the file this, and save:

   name: Main Config
   version: 1.0.0
   schema: v1
   models:
     - name: Qwen3.8 27B
       provider: openai
       model: qwen3.8-27b
       apiBase: https://api.axforge.ai/v1
       apiKey: ${{ secrets.AXFORGE_API_KEY }}
       roles: [chat, edit, apply]
       capabilities: [tool_use, image_input]
       defaultCompletionOptions:
         contextLength: 262144
     - name: GLM-5.3-Flash
       provider: openai
       model: glm-5.3-flash
       apiBase: https://api.axforge.ai/v1
       apiKey: ${{ secrets.AXFORGE_API_KEY }}
       roles: [chat, edit, apply]
       capabilities: [tool_use]
       defaultCompletionOptions:
         contextLength: 262144
     - name: MiMo-V2.6-Flash
       provider: openai
       model: mimo-v2.6-flash
       apiBase: https://api.axforge.ai/v1
       apiKey: ${{ secrets.AXFORGE_API_KEY }}
       roles: [chat, edit, apply]
       capabilities: [tool_use]
       defaultCompletionOptions:
         contextLength: 262144

   capabilities: [tool_use] lets Agent mode use the models; Continue does not know our model names, so it would not turn that on by itself.

   

4. Put your key next to it

   Create the file ~/.continue/.env (on Windows %USERPROFILE%\.continue\.env) with one line. Continue reads secrets.AXFORGE_API_KEY from it, so the key stays out of config.yaml.

   AXFORGE_API_KEY=orx_live_your_key_here

5. Pick the model

   Click the model name under the message box and choose Qwen3.8 27B.

   

6. Give it a task

   In Agent mode, ask in plain words. Continue shows its change as a diff in the file and asks: press Accept to keep it.

   

   

The settings

Which model for what: qwen3.8-27b is the everyday default and reads images, glm-5.3-flash thinks before it answers, mimo-v2.6-flash is the fastest.

Check that it works

Our three models are in the menu under the message box and a task gets done. The calls show in the console under API Keys → Recent calls within a minute.

When it does not work

Not sure which it is? The connection doctor makes seven small checks on your key and names the fix: irm https://dev.axforge.ai/assets/axforge-doctor.ps1 | iex in PowerShell, curl -fsSL https://dev.axforge.ai/assets/axforge-doctor.sh | bash on macOS and Linux.

Test a call says in one click whether a problem is your key, your balance or us.