Codex.

Codex CLI is OpenAI’s terminal agent. It speaks the OpenAI format, which is the same one NaN speaks, so it connects directly: all you have to do is declare a new provider.

You can skip all of this The NaN CLI writes this configuration for you: Setup tab, e to paste your key, space to mark Codex, c to apply.

What you need

• Codex CLI installed.
• Your NaN API key in an environment variable.

export NAN_API_KEY="sk-your-key"

Codex reads the key from the environment variable you point it at, not from the configuration file. That way it does not end up written in a file you might push to a repository by accident.

Configuration

Edit ~/.codex/config.toml:

model_provider = "nan"
model = "glm5.3-flash"
model_context_window = 1048576

[model_providers.nan]
name = "NaN"
base_url = "https://api.nan.builders/v1"
env_key = "NAN_API_KEY"
wire_api = "responses"

Four details that matter:

• wire_api = "responses" is the only value Codex still takes. Since 0.154, "chat" does not just work worse: the file does not load and Codex does not open. This page used to recommend "chat" because /responses answered in one go; it streams the answer now, except on qwen3.6 and gemma4 (see below).
• model_context_window is needed because Codex has no metadata for the cluster’s models: without it, it guesses a window and compacts the conversation long before it has to. Use the one for the model you run; they are in Models.
• The provider identifier cannot be openai, ollama or lmstudio, which are reserved. That is why it is called nan.
• base_url ends at /v1 and nothing more. Do not add the endpoint path.

Check that it works

codex

Ask it for something short, for example to list the files in the directory and summarize what the project does. If it answers, it is already working against the cluster.

If you see an authentication error, the usual cause is that NAN_API_KEY is not exported in the terminal you are launching codex from.

Switching models

You can change it without touching the file:

codex --model deepseek-v4-flash

With one catch: the model_context_window in the file does not follow the model, so a 262,144-token model keeps the window of whichever one you declared, and Codex compacts against a window that is not there.

To keep the cluster’s models at hand, each with its own window, write one file per model in ~/.codex/. Codex calls it a profile: your config.toml with that file layered on top.

# ~/.codex/nan-qwen36.config.toml
model = "qwen3.6"
model_provider = "nan"
model_context_window = 262144

codex --profile nan-qwen36

Mind the name: Codex wants “a plain name” and rejects dots, so qwen3.6 is not usable as a profile even though it is fine as a model.

The rest of your config.toml - your provider, your MCP servers, your permissions - still applies; the profile only overrides what it names. The NaN CLI writes them for you, one per chat model on the cluster, prefixed nan- and with the dots dropped: nan-glm53-flash, nan-deepseek-v4-flash, nan-mimo-v26-flash, nan-qwen36… Disconnecting Codex takes them away again.

Recommended model

glm5.3-flash for coding work. If you have the premium tier, glm5.3. For one-off questions that do not touch files, deepseek-v4-flash is more than enough.