> ## Documentation Index
> Fetch the complete documentation index at: https://docs.dimilinks.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Codex CLI integration

> Call DimiLinks GPT models from the OpenAI Codex CLI.

[Codex CLI](https://github.com/openai/codex) supports custom providers through `~/.codex/config.toml`. The two most common integration methods are shown below.

## One-click import (recommended)

The DimiLinks console can send a GPT key directly to [CC Switch](https://github.com/farion1231/cc-switch):

1. On the API Keys page, click "Import to CC Switch" for a key with no model restriction or a restriction to GPT models.
2. CC Switch automatically adds a `Codex` provider with the base URL `https://dimilinks.com/v1`.
3. Before starting Codex, run `cc-switch use codex` to route Codex through the DimiLinks OpenAI-compatible endpoint.

See [One-click import into CC Switch / Cherry Studio](/en/api-reference/integrations/ccswitch) for the deep-link structure.

## Configure `~/.codex/config.toml` manually

To manage it yourself, edit `~/.codex/config.toml` and add a provider:

```toml theme={null}
[providers.dimilinks]
name = "DimiLinks"
base_url = "https://dimilinks.com/v1"
api_key = "sk-..."
default_model = "gpt-5.5"
```

Then switch to it in Codex:

```bash theme={null}
codex provider use dimilinks
codex
```

To use DimiLinks by default, set `provider = "dimilinks"` at the top level of the configuration.

## Switch temporarily with environment variables

```bash theme={null}
export OPENAI_BASE_URL="https://dimilinks.com/v1"
export OPENAI_API_KEY="sk-..."
codex
```

This is useful for temporary troubleshooting or CI.

## Recommended models

| Use case                    | Model ID                   |
| --------------------------- | -------------------------- |
| Coding assistant            | `gpt-5.6-terra`, `gpt-5.5` |
| General chat / long context | `gpt-5.5`, `gpt-5.6-luna`  |
| Low-cost batch tasks        | `gpt-5.4-mini`             |

Treat `GET https://dimilinks.com/v1/models` as the authoritative model catalog.

## Troubleshooting

* **`401 Invalid token`:** Check whether shell quoting truncated `api_key` / `OPENAI_API_KEY`.
* **`404`:** This occurs when the base URL is set to `https://dimilinks.com/` without `/v1`. The OpenAI-compatible endpoint requires `/v1`.
* **`429 rate_limit_rpm`:** Reduce concurrency. `OPENAI_MAX_RETRIES` already backs off by default, but you can increase it.
* **Keep an official OpenAI account available as well:** Keep another provider in `config.toml` and switch with `provider use` when needed.