Coding Tools

Use KiteRouter with coding tools that support an OpenAI-compatible endpoint. Codex uses the OpenAI Responses API and can connect through a custom provider.

Share this section with teammates: https://kiterouter.com/docs/coding-tools

Before you start

Create a KiteRouter API key from Dashboard -> API Keys.
Copy the exact model ID from the Models page.
Restart the tool after changing environment variables or config files.
Test with a small prompt before launching a long agent task.

Codex

Codex reads config.toml from %USERPROFILE%\.codex\config.toml on Windows or ~/.codex/config.toml on macOS, Linux, and WSL.

toml
1model = "openai/gpt-5.6-sol"
2model_provider = "kiterouter"
3
4[model_providers.kiterouter]
5name = "KiteRouter"
6base_url = "https://kiterouter.com/api/v1"
7env_key = "KITEROUTER_API_KEY"
8wire_api = "responses"

macOS / Linux / WSL:

bash
1export KITEROUTER_API_KEY="kr-your-api-key"
2codex exec "Reply with: ready"

Windows PowerShell:

powershell
1$env:KITEROUTER_API_KEY = "kr-your-api-key"
2codex exec "Reply with: ready"

Troubleshooting

Symptom	What to check
`401` or `invalid_api_key`	Use a KiteRouter `kr-` key and restart the tool after setting the environment.
Codex config rejected	Keep provider settings in `config.toml` and `wire_api = "responses"`.
Model not found	Copy the exact model ID from the Models page.

Security: Never commit kr- keys. Prefer environment variables, OS keychain storage, or your tool's secret manager.

Ready to start building?

Get your API key and make your first request in under a minute.