---
title: "Codex Desktop Shows \"Custom\" and Hides Your Models: How to Trace and Fix It"
description: "Your custom provider works in the Codex CLI, yet Codex Desktop shows only Custom and hides your models. Walk through TOML placement, process restarts, client-side UI filtering, and four working fixes."
url: https://codingpass.ai/blog/codex-desktop-custom-model-picker
language: en
updated: 2026-11-20
---
# Codex Desktop Shows "Custom": Where Are Your Models?

You configure a third-party gateway in config.toml and the Codex CLI runs your custom model right away, yet Codex Desktop displays only Custom and leaves your models out of the dropdown. Digging past the config file reveals the filter is in the Desktop UI.

[CodingPass team](https://codingpass.ai/about) Published Nov 20, 2026 Updated Nov 20, 2026 5 min read

After wiring `~/.codex/config.toml` to a third-party gateway, you run `codex -m claude-sonnet-5-5` in the terminal and everything works. Then you open **Codex Desktop**, look at the model bar, and see only `Custom` (or `Custom High`)—with none of your custom models anywhere in the dropdown.

The natural first guess is that Desktop did not read `config.toml`, or that something in the file is invalid. Checking it step by step shows two separate layers: a pair of local config traps that genuinely break loading, and a client-side UI filter that still hides the dropdown entries even when your config is spotless.

Seeing `Custom` in the Codex Desktop bar does not mean your config failed. As long as `model` sits at the top of `config.toml`, Desktop still routes requests to that exact model ID even when the dropdown hides it.

## Rule out two local config traps first

Before blaming the Desktop app, two easy mistakes can make it look like `config.toml` is being ignored:

### 1. Placing `model` and `model_provider` below a `[table]` header

In TOML, keys belong to the top-level root only if they appear **before** the first `[model_providers.xxx]` header. If you paste `model = "claude-sonnet-5-5"` at the bottom of the file, it falls inside `[model_providers.codingpass]` instead of setting the global default, and Desktop will not pick it up.

### 2. Closing the window instead of quitting the app

Codex Desktop reads `config.toml` once at launch. Closing the window on macOS leaves the background process running, so reopening the window keeps the old settings. You need a full quit (`Cmd + Q` on macOS, or exiting from the system tray on Windows) after every edit.

## Once config is fixed, why does it still say `Custom`?

After moving the top-level keys above `[model_providers.codingpass]` and doing a full `Cmd + Q` restart, sending a test prompt reveals something telling: the request actually succeeds and reaches `claude-sonnet-5-5`, even though the badge in the UI still reads `Custom`.

Meanwhile, the `codex` CLI reading the exact same `config.toml` shows and switches models without trouble. Looking at how Desktop is built explains the split: the underlying `app-server` does load your `config.toml` and `model_catalog_json` via `model/list`, but the Electron renderer wrapping it applies its own UI gate:

- **Client-side dropdown filtering**: Before rendering the picker, the Desktop renderer checks dynamic feature flags (`use_hidden_models`, `available_models`, `default_model`) and strips any model outside the allowed list (tracked in [openai/codex#19694](https://github.com/openai/codex/issues/19694)).
- **Stricter gating in API-key-only sessions**: If you use Codex Desktop with an API key only and no active ChatGPT/OpenAI browser session, the UI switches to a stricter whitelist branch that hides custom models altogether (see [#37379](https://github.com/openai/codex/issues/37379)).

In short, routing works—the Desktop UI is just hiding non-catalog models behind a `Custom` or `Custom High` label.

## Four ways to work around it

Once you know the backend is routing correctly, stop fighting `config.toml` formatting and pick the workaround that matches how often you switch models:

| Approach | When to use | Trade-off |
| --- | --- | --- |
| Hardcode `model` in `config.toml` | You mostly stick to one custom model in Desktop | UI shows `Custom`; switching requires editing the file + `Cmd + Q` |
| Keep a ChatGPT session logged in | You want to lift the API-key-only UI gate | Requires signing in with an OpenAI account (Free/Go tier is enough) |
| Use `codex` CLI (`-m` / `--profile`) | You switch models or providers frequently | Terminal TUI instead of Desktop GUI |
| Community `app.asar` patchers | You want custom entries inside the Desktop dropdown | Unofficial; overwritten on every Codex Desktop update |

### 1. Hardcode `model` at the top and ignore `Custom`

If you mostly stay on one model in Desktop—such as `claude-sonnet-5-5` or `gpt-6-2-sol` via CodingPass—keep `model_provider` and `model` at the very top of `~/.codex/config.toml` above any `[table]`:

```
model_provider = "codingpass"
model = "claude-sonnet-5-5"

[model_providers.codingpass]
name = "CodingPass"
base_url = "https://codingpass.ai/v1"
env_key = "CODINGPASS_API_KEY"
wire_api = "responses"
```

Quit completely (`Cmd + Q`) and reopen. Ignore the `Custom` badge and send prompts as usual.

### 2. Keep an official ChatGPT session signed in

To lift the API-key-only restriction, keep a standard ChatGPT account signed in inside the app alongside your custom `config.toml` provider. The active session satisfies the UI check while your requests still route through the provider in `config.toml`.

### 3. Switch models in the CLI with `-m` or `--profile`

The `codex` CLI has no Desktop renderer filter. Since Codex `0.134.0`, profiles live in separate files, so you can keep your main config on official OpenAI and put CodingPass in `~/.codex/cp.config.toml`:

```
codex --profile cp -m claude-sonnet-5-5
```

### 4. Community `app.asar` patches (last resort)

Because the filter lives inside the local Electron `app.asar` bundle, community tools such as `CodexUse` toggle `use_hidden_models` so custom models appear in the dropdown. Every Codex Desktop update overwrites `app.asar`, making this fragile for daily use.

For full `config.toml` examples, environment variables, and available models per tier, see the [Codex setup guide](https://codingpass.ai/tools/codex) and [how allowances and caps work](https://codingpass.ai/usage-limits).

Written by CodingPass team

We run CodingPass and test each guide against the latest stable release of the tool before we publish it. Spotted something out of date? Write to [support@codingpass.ai](mailto:support@codingpass.ai).

## Related reading.

Guide

### [Codex setup guide](https://codingpass.ai/tools/codex)

config.toml setup, env\_key vs experimental\_bearer\_token, and model IDs per plan.

Rules

### [How allowances and caps work](https://codingpass.ai/usage-limits)

Allowances and caps for every plan and model, plus the 429 response.

Models

### [All models](https://codingpass.ai/models)

Model IDs, required tiers, and monthly allowances.
