Aider on Codex Pooler

Aider uses the OpenAI-compatible route with the openai/ model prefix.

Before you start

• Aider installed and ready to use.
• A Codex Pooler URL reachable from the client.
• A Pool API key and a model available to that Pool.

Use a Pool API key for model requests. Operator MCP access is optional and uses a separate token.

Configure the connection

Put the stable route settings in .aider.conf.yml; Aider loads this file from your home directory, then the git repo root, then the current directory, with later files taking priority. Use --config <filename> only when you want one explicit config file.

Set CODEX_POOLER_API_KEY to your Pool API key. Keep the key out of the YAML file. Export it in the shell, or put it in a gitignored .env file that Aider can load:

export OPENAI_API_KEY="$CODEX_POOLER_API_KEY"

For a deployed instance, use:

.aider.conf.yml

model: openai/gpt-6-sol
openai-api-base: https://codex-pooler.example.com/v1

For local setup, change openai-api-base to http://localhost:4000/v1.

Choose a model

Keep the openai/ prefix when selecting a model available to your Pool.

Aider’s .aider.conf.yml route settings do not carry context or output limits. If your installed Aider version does not recognize gpt-6-sol, use Aider’s separate model metadata JSON file for model behavior and limits instead of adding unsupported context fields to the main config.

.aider.model.metadata.json

{
  "openai/gpt-6-luna": {
    "max_tokens": 828400,
    "max_input_tokens": 700400,
    "max_output_tokens": 128000,
    "litellm_provider": "openai",
    "mode": "chat",
    "supports_function_calling": true,
    "supports_vision": true,
    "supports_reasoning": true
  },
  "openai/gpt-6-sol": {
    "max_tokens": 828400,
    "max_input_tokens": 700400,
    "max_output_tokens": 128000,
    "litellm_provider": "openai",
    "mode": "chat",
    "supports_function_calling": true,
    "supports_vision": true,
    "supports_reasoning": true
  },
  "openai/gpt-6-astra": {
    "max_tokens": 828400,
    "max_input_tokens": 700400,
    "max_output_tokens": 128000,
    "litellm_provider": "openai",
    "mode": "chat",
    "supports_function_calling": true,
    "supports_vision": true,
    "supports_reasoning": true
  }
}

When the Pool’s /v1/models entry provides context_length, use that per-model effective value as the authoritative max_tokens value. The 828400 values above are long-profile examples for models whose selected Pool catalog source reports an 872000-token raw ceiling; the explicit 700400 input and 128000 output limits add up to that window. Provider accounts can temporarily report different ceilings for the same model, and a selected 272000-token profile exposes 258400, so replace all three related limits together when the endpoint reports a different value.

Verify the connection

Check Aider from a repository with a real file edit. The command should only need the one-off prompt when the config file is present:

aider \
  --message 'Create a file named aider-ok.txt containing exactly: aider ok. After the file exists, reply with exactly: aider ok' \
  --yes-always \
  --no-auto-commits \
  --no-git \
  --no-browser \
  --no-gui \
  --no-analytics

The check is only useful if aider-ok.txt exists with the expected content; a text reply alone does not prove Aider can edit through the configured model path.

In Codex Pooler’s request logs, match the request time, API key, model, and final status to your test. A reply alone does not confirm that the client used your Pooler instance.

Compatibility notes

The Pool API key authenticates /v1 model requests. Do not use an operator MCP token as the OpenAI API key.

For shared route support and limits, see OpenAI-compatible SDKs.