Connecting in Codex CLI

All Explyt gateway models are available in Codex CLI, including Anthropic models. The ChatGPT app works only with OpenAI models — see Codex in ChatGPT.

Open or create the file ~/.codex/config.toml, where ~ is your home directory
- If the file already contains settings (the ChatGPT app creates them), do not delete them

Add three lines to the very beginning of the file:

model = "auto"
model_provider = "explyt"
model_catalog_json = "./model-catalog-full.json"

Add the block below to the very end of the same file:
```
[model_providers.explyt]
name = "explyt"
base_url = "https://api.explyt.ai/openai/api"
wire_api = "responses"
requires_openai_auth = true
```
- The base_url field already contains the OpenAI-compatible URL https://api.explyt.ai/openai/api

Next to config.toml, create the file model-catalog-full.json with the list of Explyt models

Download the ready-made model-catalog-full.json file — or copy its contents manually:

Contents of model-catalog-full.json

{
  "models": [
    {
      "slug": "auto",
      "id": "auto",
      "display_name": "Explyt Auto",
      "description": "Automatic model selection: high quality with maximum availability",
      "context_window": 372000,
      "max_output_tokens": 32768,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 1,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "OpenAI/gpt-5.6-sol",
      "id": "OpenAI/gpt-5.6-sol",
      "display_name": "OpenAI GPT-5.6 Sol",
      "description": "The highest quality among OpenAI models",
      "context_window": 372000,
      "max_output_tokens": 32768,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 2,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "OpenAI/gpt-5.6-terra",
      "id": "OpenAI/gpt-5.6-terra",
      "display_name": "OpenAI GPT-5.6 Terra",
      "description": "Balance of quality and speed among OpenAI models",
      "context_window": 372000,
      "max_output_tokens": 32768,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 3,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "OpenAI/gpt-5.6-luna",
      "id": "OpenAI/gpt-5.6-luna",
      "display_name": "OpenAI GPT-5.6 Luna",
      "description": "The fastest and cheapest among OpenAI models",
      "context_window": 372000,
      "max_output_tokens": 32768,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 4,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "OpenAI/gpt-5.5",
      "id": "OpenAI/gpt-5.5",
      "display_name": "OpenAI GPT-5.5",
      "description": "Previous-generation OpenAI model",
      "context_window": 272000,
      "max_output_tokens": 16384,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 5,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "Anthropic/fable-5",
      "id": "Anthropic/fable-5",
      "display_name": "Anthropic Fable 5",
      "description": "The most powerful Anthropic model",
      "context_window": 1000000,
      "max_output_tokens": 128000,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 6,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "Anthropic/opus-5",
      "id": "Anthropic/opus-5",
      "display_name": "Anthropic Opus 5",
      "description": "High quality, cheaper than Fable 5",
      "context_window": 1000000,
      "max_output_tokens": 65536,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 7,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "Anthropic/sonnet-5",
      "id": "Anthropic/sonnet-5",
      "display_name": "Anthropic Sonnet 5",
      "description": "Balance of quality and speed among Anthropic models",
      "context_window": 1000000,
      "max_output_tokens": 65536,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 8,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "low"
        },
        {
          "effort": "medium",
          "description": "medium"
        },
        {
          "effort": "high",
          "description": "high"
        },
        {
          "effort": "xhigh",
          "description": "xhigh"
        }
      ]
    },
    {
      "slug": "Anthropic/haiku-4.5",
      "id": "Anthropic/haiku-4.5",
      "display_name": "Anthropic Haiku 4.5",
      "description": "The fastest and cheapest among Anthropic models",
      "context_window": 264000,
      "max_output_tokens": 64000,
      "base_instructions": "default",
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 9,
      "support_verbosity": false,
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      },
      "experimental_supported_tools": [],
      "supported_reasoning_levels": [
        {
          "effort": "none",
          "description": "none"
        },
        {
          "effort": "low",
          "description": "low"
        }
      ]
    }
  ]
}

To add a model, copy any block and put your own slug value in it.

The priority field sets the order in the model picker: the lower the number, the higher the model in the list
Full list of models: https://api.explyt.ai/openai/api/models
If the error failed to parse model_catalog_json appears after a Codex update, add the field named in the error message to every model

Open or create the file ~/.codex/auth.json and fill it with the contents below:
```
{
  "auth_mode": "apikey",
  "OPENAI_API_KEY": "<YOUR_API_KEY>"
}
```
- Replace <YOUR_API_KEY> with the API key from your personal account. The key is in the Connect to Explyt block of your personal account, the Copy key button. Details: where to get the URL and key
- No OpenAI account is needed: the key is used only for requests to the Explyt gateway
- If you previously signed in through a ChatGPT account, run codex logout and create the file again
Start Codex:
```
codex
```
To choose a model, use /model
- auto – automatic model selection: high quality with maximum availability
- OpenAI/gpt-5.6-sol – the highest quality among OpenAI models
- OpenAI/gpt-5.6-terra – balance of quality and speed among OpenAI models
- OpenAI/gpt-5.6-luna – the fastest and cheapest among OpenAI models
- OpenAI/gpt-5.5 – previous-generation OpenAI model
- Anthropic/fable-5 – the most powerful Anthropic model
- Anthropic/opus-5 – high quality, cheaper than Fable 5
- Anthropic/sonnet-5 – balance of quality and speed among Anthropic models
- Anthropic/haiku-4.5 – the fastest and cheapest among Anthropic models
- The list shows eight models at a time; scroll down to see the rest
Send any message and make sure the model responds
- If the error 404 Not Found appears, the key is wrong or revoked. Check the contents of ~/.codex/auth.json. If that does not help, reissue the key in your personal account (the Reissue link in the Connect to Explyt block) and paste the new one

If you use both Codex CLI and the ChatGPT app

They share the config.toml file, and the app can work only with OpenAI models. To keep only the working models in the app while all models stay available in Codex CLI, split the catalogs:

In config.toml, point to the catalog for the app: model_catalog_json = "./model-catalog.json" — and put the model-catalog.json file from the Codex in ChatGPT guide next to it
Keep the full catalog model-catalog-full.json in place as well
Create the file ~/.codex/full.config.toml with a single line:
```
model_catalog_json = "./model-catalog-full.json"
```
Start Codex CLI with this profile:
```
codex --profile full
```

Requests from Codex CLI spend Explyt subscription minutes the same way as requests from the plugin. The balance is shown in your personal account.

For errors, see Error messages.