Local-first routing for AI agents

Why routing should stay close to your tools

Teams often combine hosted models, local Ollama, private endpoints, and several subscriptions. Each tool handles those connections differently, which makes outages and rate limits harder to recover from.

TEKIZ.AI puts those routes in one place, close to the machines and accounts you already control.

Choose where your provider access lives

If you use a hosted model marketplace, check how it handles these three choices:

Credentials. Check where provider keys are stored and which service receives your requests.
Route order. Check whether you can choose which local or cloud model runs first after a failure.
Local models. Check whether local Ollama and private Tailnet models can serve the same tools.

What local-first routing means

TEKIZ.AI runs on your machine, server, Tailnet host, or as a hosted service. It exposes one OpenAI-compatible endpoint. Your tools point at it. The router can:

Select models by task, speed, context size, file support, and your preferences.
Fail over across authorized providers when one is down, slow, or rate-limited, without switching models mid-stream.
Route local Ollama, Ollama Cloud through local Ollama, OpenAI, Anthropic, Gemini, NVIDIA NIM, private gateways, and OpenRouter BYOK routes.
Keep provider credentials on your machine when you run the router there. Hosted TEKIZ.AI API keys manage account access, usage limits, and request history.
Record routing details so you can see which provider and model served a request.

For Codex and coding agents

Use one base URL and stable profiles such as tekizai/frontier while routing behind the scenes across healthy authorized providers.

For local Ollama fallback

Keep local models in the fallback chain for privacy, cost control, and continuity when cloud providers rate-limit.

For hosted teams

Hosted TEKIZ.AI provides API keys, usage limits, request history, health checks, and retry routes. Managed provider access requires separate provider approval and a confirmed plan.

Connect a local router

With access to a configured router installation, start it in one terminal. Use a second terminal to check which models are available. Ask about installation access if you need it.

python3 router.py --port 8790

export OPENAI_BASE_URL=http://localhost:8790/v1
export OPENAI_API_KEY=local-router
curl "$OPENAI_BASE_URL/models" \
  -H "Authorization: Bearer $OPENAI_API_KEY"

To use Codex, create a separate profile with this local base URL. The Codex router guide explains the hosted and local profiles.

What the hosted plan includes

Router installation is currently available through a private setup review. Hosted plans include API keys, usage limits, request history, and health checks. Your own provider accounts and local models stay on the router you run. Ask about managed access if you need TEKIZ.AI to arrange a provider route.

Next steps

Start with the hosted API quickstart, configure Codex, compare TEKIZ.AI vs OpenRouter, or estimate routing fit with the calculator.