Start with hosted models
Create a TEKIZ.AI key and use the Codex profile below. Hosted requests use your TEKIZ.AI account and its available models and quota. You do not need a separate provider key to start.
Codex CLI routing
Use a TEKIZ.AI API key for hosted models. If you want to route through your own provider accounts or local models, run the router on your machine or Tailnet. Codex connects to either route through the Responses API.
Create a TEKIZ.AI key and use the Codex profile below. Hosted requests use your TEKIZ.AI account and its available models and quota. You do not need a separate provider key to start.
Run TEKIZ.AI on http://127.0.0.1:8790/v1/ or a
Tailnet host to use provider accounts, authorized OAuth profiles,
or local Ollama models. Provider usage follows your own accounts
and billing.
TEKIZ.AI can try another eligible model when one rate-limits or fails, if another eligible route is available in the deployment you chose.
mkdir -p ~/.codex if ! grep -Fqx '[model_providers.tekizai]' ~/.codex/config.toml 2>/dev/null; then cat >> ~/.codex/config.toml <<'TOML' [model_providers.tekizai] name = "TEKIZ.AI hosted" base_url = "https://api.tekiz.ai/v1/" env_key = "TEKIZAI_API_KEY" wire_api = "responses" TOML fi cat > ~/.codex/tekizai.config.toml <<'TOML' model_provider = "tekizai" model = "tekizai/auto" TOML # Shell export TEKIZAI_API_KEY=sk_tekiz_your_generated_key # Plain codex keeps using ChatGPT. TEKIZ.AI is explicit. codex --profile tekizai
Coding profiles follow the tool's file and instruction requirements. TEKIZ.AI chooses among eligible providers by availability, speed, and model support.
Run your own router for Codex and OpenClaw on local workspaces, Umbrel hosts, or Tailnet machines. Each client points to the router address you control.
TEKIZ.AI can complete the official Codex device flow for an authorized OpenAI account. It never grants access on its own; bring your subscription or use hosted routing with a TEKIZ.AI API key.
Keep the hosted profile above for TEKIZ.AI account models. For your own provider accounts or local models, create a separate Codex profile with the base URL of your local or Tailnet router. Each profile uses the models and limits of the deployment it points to.
Create an API key, open the Codex guide, copy the hosted quickstart, or estimate routing fit.