Quick setup
Quick setup
Add this line at the very beginning of config.toml.
openai_base_url = "https://codex-api-shop.space/codex"- Configure the OpenAI-compatible provider
- Save config.toml
- Fully restart Codex
Codex
Connection guide
Connect your key to Codex App, Codex CLI, or the Codex extension for VS Code.
Connection steps
Connection steps
The setup is identical across official Codex clients.
Open config.toml
Open Windows File Explorer, paste the path below into the address bar, and press Enter.
%USERPROFILE%\.codex\config.tomlConfigure the OpenAI-compatible provider
Paste this line at the very beginning of config.toml. If openai_base_url already exists, replace its value.
openai_base_url = "https://codex-api-shop.space/codex"Save config.toml
Save your config.toml changes before restarting Codex.
Fully restart Codex
The settings take effect only after the application starts again.
1 Close Codex
Close the application completely.
2 Check Task Manager
If Codex is still running, end the process.
3 Launch Codex
The endpoint configuration takes effect on startup.
Sign in with your API key
When Codex starts, choose API key sign-in: “Use another sign-in method” → enter your API key → “Continue”. Done: Codex will use the configured API.
Restore defaults
Return to the default connection
Remove openai_base_url from config.toml or clear the environment variable, then restart Codex.
openai_base_url = ""Other IDEs and AI agents
Connect an OpenAI-compatible client
Set the Base URL and your API key in the application's provider settings.
Base URL: https://codex-api-shop.space/codex/v1
API Key: YOUR_API_KEY- Open provider settings
- Paste the Base URL and API key
- Save and test the connection
Claude
Quick setup
Enable developer mode in the Claude for Windows app and it starts working through our gateway.
Gateway base URL: https://codex-api-shop.space/codex/v1- Sign out of your account
- Enable developer mode
- Fill the fields and apply
Connection steps
Claude Desktop
Enable developer mode in the Claude for Windows app and it starts working through our gateway.
Sign out of your account
Open the Claude for Windows app. If you are already signed in, sign out first and stop on the sign-in screen — do not press “Sign in”.
Enable developer mode
Open the “Help” menu in the top-left corner (or the three-line button), then “Troubleshooting” and “Enable Developer mode”.
Help → Troubleshooting → Enable Developer modeOpen the third-party API settings
Once developer mode is on, a “Developer” item appears in the top menu. Click “Developer” → “Configure third-party inference”.
Developer → Configure third-party inferenceFill the fields and apply
Paste the gateway address and your API key, then click “Apply locally”. A key issued for the Claude server (Kiro Claude group) is required.
Gateway base URL: https://codex-api-shop.space/codex/v1Gateway API key: sk-...Apply locallyHow to restore the default connection
How to restore the default connection
Open “Developer” → “Configure third-party inference” again, restore the previous field values and click “Apply locally”.
Available models
Available models
claude-opus-5, claude-sonnet-5 and claude-haiku-4-5. The exact list depends on your key.
ZCode
ZCode — connecting GLM
The provider is added by hand: address, key and three GLM models.
https://codex-api-shop.space/codex/v1- Settings → Models → Custom Provider → Add provider.
- Paste the Base URL from the line below and your API key.
- Add the GLM models to Model list and save the provider.
Connection steps
ZCode — connecting GLM
Five steps; only the ZCode settings change.
Open the custom providers section
Settings → Models → Custom Provider. This section is for manually added providers; official ones never show up here.
Press Add provider
ZCode creates an empty provider card — we fill it in on the next steps.
Set the Base URL
Our gateway address. It is OpenAI-compatible: no extra ports, proxies or VPN required.
https://codex-api-shop.space/codex/v1Paste your API key
Copy the sk-… key from the account area — the same key works for Codex, Claude Desktop and the rest.
API Key: sk-…Add the GLM models to Model list
List the models one per line — copy the whole list if you like.
Model listglm-5.3 glm-5.2 glm-5.3-flash
Save the provider and pick the model you need from the model list.
If the model does not answer
What to check
The address is pasted whole, including /codex/v1; the key has no stray spaces and is active in the account area; the model is in Model list.
One key
The same key for other clients
The key works with any OpenAI-compatible client: Codex, Cursor, VS Code, OpenCode, ZCode and DeepSeek Harness — only the endpoint differs.
DeepSeek Harness
DeepSeek Harness — connecting DeepSeek
The provider is added by hand: address, key and three DeepSeek models.
https://codex-api-shop.space/codex/v1- Settings → Models → Add provider.
- Paste the Base URL from the line below and enter your API key.
- Add the DeepSeek models, save the settings and check the connection.
Connection steps
DeepSeek Harness — connecting DeepSeek
Five steps: the DeepSeek Harness settings only.
Open Settings → Models
Add provider lives in the Models section, next to the list of providers you already have.
Press Add provider
Give the provider a clear name (for example, keydex) — that is how it appears in the model list.
Set the Base URL
Our gateway address: OpenAI-compatible (api: openai-completions), no VPN or proxy needed.
https://codex-api-shop.space/codex/v1Enter your API key
The sk-… key is in the account area; an active key is ready to use right away.
API Key: sk-…Add the DeepSeek models to the list
Copy the whole list or type the models in one by one.
Model listdeepseek-v4-pro deepseek-v4-flash deepseek-v4.1-flash
Check the connection
A short request
Save the settings and ask the chosen model anything: if the answer arrives, the provider is set up correctly.