OpenAI-compatible provider

Continue can use TEKIZ.AI as an OpenAI-compatible model provider with apiBase set to https://api.tekiz.ai/v1 or local port 8790.

Use Ollama on your router

On a router you run, choose a local model for routine edits and an authorized cloud route when the work needs more capacity.

When a Continue route reaches a limit

If a provider key or model reaches a limit, TEKIZ.AI can try another configured route. Continue keeps the same provider settings.

Continue configuration file

# ~/.continue/config.yaml
name: TEKIZ.AI
version: 0.0.1
schema: v1

models:
  - name: TEKIZ.AI Frontier
    provider: openai
    model: tekizai/frontier
    apiBase: https://api.tekiz.ai/v1
    apiKey: sk_tekiz_your_generated_key
  - name: TEKIZ.AI Auto
    provider: openai
    model: tekizai/auto
    apiBase: https://api.tekiz.ai/v1
    apiKey: sk_tekiz_your_generated_key

# Local router alternative:
# apiBase: http://localhost:8790/v1
# apiKey: local-router
# Store a generated key in Continue's secret storage when available;
# never commit a workspace config that contains one.
# Continue loads config.yaml before the older config.json format.

Normal coding sessions

Use balanced routing for everyday Continue chat and edits, then escalate to stronger routes when quality or context needs rise.

Use more than one provider credential

A router you run can use your authorized provider credentials to handle rate limits and provider outages.

Use accounts you are allowed to use

Put authorized provider credentials on a router you control. A hosted TEKIZ.AI key uses the models available to your account.

Keep one Continue entry for the router you choose

A router you run can choose approved local or cloud models for new requests and show which route handled each one. Hosted accounts use a separate endpoint and key.

Next steps

Create an API key, review local router setup, copy the hosted quickstart, or estimate routing fit.