Use Aider with any model

Set it up

1. 01

   The configuration surface

   Aider takes the base URL either as a flag or from the environment:

   bash

   export OPENAI_API_BASE=https://api.hopscotchlabs.ai/v1
   export OPENAI_API_KEY=ub_live_YOUR_KEY_HERE

   The flag form is --openai-api-base, and its own environment variable is AIDER_OPENAI_API_BASE.

   Include the version segment in the value.

2. 02

   The three models

   It configures up to three models separately, and each one needs its own pinned id:

   --model

   The main model.

   --editor-model

   Applies the edits in architect mode, where the main model proposes them.

   --weak-model

   Commit messages and chat-history summarisation.

   Set all three explicitly if you use architect mode or let Aider write your commit messages.

3. 03

   The model id, and the prefix collision

   Aider's documented way of naming a model on a compatible endpoint is to prefix it with openai/.

   Our ids already begin with the provider that serves them, and for models served by OpenAI that provider is also openai. So a pinned id and Aider's prefix convention produce a doubled first segment:

   bash

   aider --model openai/openai/gpt-4o-mini

   We did not verify what reaches the wire in that case.

   An id whose provider is not openai does not have this problem, because the prefix and the provider are then different strings.

4. 04

   Keep the key out of the repository

   Aider reads .aider.conf.yml and .env from your home directory, your repository root and the current directory, in that order, with the later files overriding. Two of those three locations are inside the repository. Aider can add its own files to .gitignore for you, and the safe habit is the home-directory copy plus the environment variables above.

These models support tool calling and take at least 128K tokens of context. Prices are per million tokens.

What changes when Aider runs through Hopscotch