Connect → llm

Use AxForge with llm

llm runs prompts from the command line and keeps a log of them. One entry in its extra-openai-models.yaml adds an AxForge model.

Set it up

1. Install llm

   pip install llm

2. Add the AxForge model

   Create extra-openai-models.yaml in llm's folder, the one llm logs path shows (on Linux ~/.config/io.datasette.llm/):

   - model_id: axforge
     model_name: qwen3.8-27b
     api_base: https://api.axforge.ai/v1
     api_key_name: axforge

   model_id is the name you type after -m; model_name is ours. Add more entries the same way, for example axforge-glm for glm-5.3-flash.

3. Store your key

   llm keys set axforge

   Paste the key when it asks. llm keeps it in its own key file under the name axforge, the api_key_name above.

4. Ask

   llm -m axforge "Say hello in five words"

   

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. To make it the default: llm models default axforge.

Check that it works

llm -m axforge answers, and llm logs -n 1 shows the prompt and reply. The call shows 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.