Codex can talk to LM Studio via the OpenAI-compatible POST /v1/responses endpoint. See: OpenAI-compatible Responses endpoint.

Codex configured to use LM Studio via the OpenAI-compatible API

Pro Tip

Have a powerful LLM rig? Use LM Link to run Codex from your laptop while the model runs on your rig.

Make sure LM Studio is running as a server (default port 1234).

You can start it from the app, or from the terminal with lms:

lms server start --port 1234

Run Codex as you normally would, but with the --oss flag to point it to LM Studio.

Example:

codex --oss

By default, Codex will download and use openai/gpt-oss-20b.

Pro Tip

Use a model (and server/model settings) with more than ~25k context length. Tools like Codex can consume a lot of context.

You can also use any other model you have available in LM Studio. For example:

codex --oss -m ibm/granite-4-micro

If you're running into trouble, hop onto our Discord