OpenAI-compatible setup

Aider can use OPENAI_API_BASE=https://api.tekiz.ai/v1 with a hosted generated sk_tekiz_* key, or OPENAI_API_BASE=http://127.0.0.1:8790/v1 for local routing.

Use Ollama on your router

On a router you run, put a capable local model first and configure an authorized cloud route for requests it cannot handle.

When an Aider route reaches a limit

If a model or provider key reaches a limit, a new request can use another eligible route you configured.

Configure Aider

export OPENAI_API_BASE=https://api.tekiz.ai/v1
export OPENAI_API_KEY=sk_tekiz_your_generated_key

# Let TEKIZ.AI select by policy.
aider --model openai/auto

# Or point at a local TEKIZ.AI on port 8790:
# export OPENAI_API_BASE=http://127.0.0.1:8790/v1
# export OPENAI_API_KEY=local-router
# aider --model openai/auto

Optional Aider configuration file

Save this YAML as ~/.aider.conf.yml. It is a file example only. Do not paste it into your terminal.

model: openai/tekizai/frontier
openai-api-base: https://api.tekiz.ai/v1

Large codebase changes

Escalate from local coder models to stronger cloud routes when refactors need more context, quality, or reliability.

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 Aider connection to your router

A router you run can choose among your approved providers and local models for each new request. Hosted accounts use a separate TEKIZ.AI endpoint and key.

Next steps

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