🎉 Launch offer — limited time 🔥
ModelGo
ModelGo
Get Started

Codex

Codex is OpenAI's command-line AI coding assistant. With a custom model_provider, Codex CLI can send Responses API requests to ModelGo.

Before you start

  • Install Node.js 18 or later.
  • Create an API key in the ModelGo Console.
  • Confirm a logical model name allowed for the API key in the Model Catalog.

1. Install Codex

Run this command in macOS, Linux, or Windows:

bash
npm install -g @openai/codex

Verify the installation:

bash
codex --version

If Codex shows an upgrade prompt on first launch, choose Skip and finish the ModelGo setup first.

Skip the Codex upgrade prompt

2. Configure ModelGo

Codex reads its user-level model and provider settings from ~/.codex/config.toml. Create the file first:

macOS / Linux

bash
mkdir -p ~/.codex
touch ~/.codex/config.toml
${EDITOR:-vi} ~/.codex/config.toml

Windows PowerShell

powershell
New-Item -ItemType Directory -Force "$env:USERPROFILE\.codex"
notepad "$env:USERPROFILE\.codex\config.toml"

Paste the following into config.toml, replacing YOUR_MODELGO_MODEL with a logical model name allowed for the current API key:

toml
model_provider = "modelgo"
model = "YOUR_MODELGO_MODEL"

[model_providers.modelgo]
name = "ModelGo"
base_url = "https://api.modelgo.ai/v1"
env_key = "MODELGO_API_KEY"
wire_api = "responses"

The base_url is ModelGo's OpenAI-compatible API root. Codex appends /v1/responses when it sends a request.

3. Set the API key

Store your ModelGo API key in the MODELGO_API_KEY environment variable. Do not put the real key directly in config.toml.

macOS / Linux (zsh)

bash
echo 'export MODELGO_API_KEY="YOUR_MODELGO_API_KEY"' >> ~/.zshrc
source ~/.zshrc

For Bash, replace ~/.zshrc with ~/.bashrc or ~/.bash_profile.

Windows PowerShell

powershell
[Environment]::SetEnvironmentVariable("MODELGO_API_KEY", "YOUR_MODELGO_API_KEY", "User")
$env:MODELGO_API_KEY = [Environment]::GetEnvironmentVariable("MODELGO_API_KEY", "User")

Check that the variable is set without printing the key:

bash
test -n "$MODELGO_API_KEY" && echo "MODELGO_API_KEY is set"

4. Start and verify

Change to a local project directory and run:

bash
cd /path/to/your/project
codex

When Codex asks for permission to work in the project, trust the directory as appropriate. After the welcome screen appears, send a simple coding request such as “Describe this project in three sentences.”

Codex project welcome screen

A normal model response confirms that ModelGo is connected.

Start a conversation in Codex

To verify which models the API key can call:

bash
curl https://api.modelgo.ai/v1/models \
  -H "Authorization: Bearer $MODELGO_API_KEY"

Troubleshooting

Provider not found at startup

Make sure the file is the user-level ~/.codex/config.toml, and that model_provider = "modelgo" matches [model_providers.modelgo].

401 or authentication failed

Check that MODELGO_API_KEY is set in the current terminal and contains no extra spaces or newlines.

403 or model unavailable

Make sure model is a logical ModelGo model name allowed by the policy attached to the API key.

404 or incorrect endpoint path

Set base_url to https://api.modelgo.ai/v1. Do not include /responses or /v1/responses; Codex appends the path.

Chat wire API deprecation warning

Add wire_api = "responses" under [model_providers.modelgo], then upgrade Codex CLI:

bash
npm install -g @openai/codex@latest

400 invalid_encrypted_content

This usually means the conversation contains encrypted context created by the original upstream account, but the current request was handled by a different upstream account.

Check whether the API key or Base URL changed, or whether a proxy or account pool switched upstream accounts. If a switch occurred, start a new conversation instead of continuing or resuming the existing one.

Related docs