Skip to main content
Aider speaks the OpenAI Chat Completions dialect, so it runs on Sideren over the OpenAI-compatible route: an openai/-prefixed catalog id and the gateway as the API base (including /v1).

​
One command

The setup helper writes ~/.aider.conf.yml on the OpenAI-compatible route, including weak-model and editor-model slots. See setup helper.

​
By hand

Configure ~/.aider.conf.yml with an openai/-prefixed model id and the gateway as the API base (including /v1):
~/.aider.conf.yml
Or per-invocation: aider --model openai/@sdn/glm-5 --openai-api-base https://api.sideren.io/v1.

​
Verify

Launch aider in a repo and ask it to read a file. To confirm the key works against the gateway without aider in the loop: