OpenAI Codex

Prepare in the dashboard

1. Sign in to dashboard.koboillm.com with your email and password, then select your team at the top.
2. Open API Keys → Create API key. Enter a Key name; the key budget is optional. The defaults are No expiry and All Team Models. Select Create and save the full key, which is shown once.
3. Copy an accessible model name from Model List. Choose a model that supports this guide's endpoint; API Quickstart also provides request examples.
4. After running your application, open Logs in the same team, select a time range, and use View details on a request to check its key, tokens, and recorded spend.

OpenAI-compatible base URL: https://api.koboillm.com/v1. Follow the client-specific URL format below. The dashboard address is for your account; applications use the API key, not your account password.

Show the current key creation form

Actual dashboard interface with fictional demonstration data. Click to enlarge.

Model names and provider prices in examples are reference values. Availability, endpoint support, and final recorded costs depend on your key and request.

Create a key in API Keys on the KoboiLLM dashboard, and check its available models. Use a model compatible with Responses and tool calling for Codex.

Install and configure

npm install -g @openai/codex

Add this provider to your user configuration at ~/.codex/config.toml (Windows: %USERPROFILE%\.codex\config.toml). Merge it with existing settings without duplicating TOML keys. Place the top-level model and model_provider before table sections. Adjust the model name to match your key’s access.

model = "gpt-5.6-luna"
model_provider = "koboillm"

[model_providers.koboillm]
name = "KoboiLLM"
base_url = "https://api.koboillm.com/v1"
env_key = "KOBOILLM_API_KEY"
wire_api = "responses"

env_key reads the credential from an environment variable; wire_api selects Responses. Put provider settings in the user configuration, not project configuration. See the official Codex configuration reference and provider configuration.

Set the key and run

Linux/macOS:

export KOBOILLM_API_KEY="sk-xxxxxx"
codex

Windows PowerShell:

$env:KOBOILLM_API_KEY="sk-xxxxxx"
codex

Use your team’s KoboiLLM key. The provider settings above determine where requests go; changing a base URL in an unrelated SDK example does not configure Codex.

Check usage and connection issues

• 401: check the key, whitespace, and environment of the terminal running Codex.
• Model not found: match the exact accessible model name and choose a model supporting Responses.
• Budget reached: check team credit and key/member limits in the dashboard.
• Review Logs and Usage after requests finish. Chat with Responses can help check connectivity, but does not test every Codex agent feature.