Local Ollama stays local

Run TEKIZ.AI beside your local Ollama runtime and point Codex, OpenClaw, Cursor, Aider, Continue, OpenHands, or any OpenAI SDK client at one local base URL.

Add Ollama Cloud if you use it

Configure Ollama Cloud on your own router to make its models available alongside local Ollama and other services you approve.

When a cloud model reaches a limit

If a cloud model hits a retryable rate limit, TEKIZ.AI can try another configured key or provider, including an eligible local Ollama model.

Start your local router

Run this from your configured router installation. Leave it running, then use a second terminal for the model check below.

export OLLAMA_HOST=http://127.0.0.1:11434
python3 router.py --port 8790

In a second terminal, check the models your router can use:

export OPENAI_BASE_URL=http://127.0.0.1:8790/v1
export OPENAI_API_KEY=local-router

curl "$OPENAI_BASE_URL/models" \
  -H "Authorization: Bearer $OPENAI_API_KEY"

Use more than one API key

Add several OpenAI, Anthropic, Gemini, or compatible keys. TEKIZ.AI Router spreads requests across keys that are working and pauses only the one that is rate-limited.

Send files to services that accept them

Images, audio, video, and documents are sent only to models that can handle that kind of input.

Stable model names

Use a profile such as tekizai/frontier or name an Ollama model directly. TEKIZ.AI checks availability and falls back according to your settings.

Why put TEKIZ.AI in front of Ollama?

TEKIZ.AI lets several tools use the same local Ollama endpoint. You can add approved cloud models, keep provider keys on your router, and reach the router over a private Tailnet. It can try another eligible route when one is configured.

Next steps

Create an API key, read the hosted/local quickstart, see the self-hosted path, or compare OpenRouter.

Stay within your approved services

If your company approves only Ollama, keep that boundary. TEKIZ.AI can reduce unnecessary token processing and make better use of existing compute.