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.

Local Ollama fallback

Keep coding-strong local models first, then fail over to authorized cloud routes for larger edits, long context, or degraded local capacity.

Keep working when an account is busy

When an Aider route, provider key, or model reaches a limit, TEKIZ.AI Router can choose another working route automatically.

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 account key

Authorized credential pools can load balance and fail over on rate limits, provider health, latency, and policy.

Use accounts you are allowed to use

TEKIZ.AI does not grant unauthorized OpenAI, Anthropic, Gemini, NVIDIA, Ollama Cloud, or other provider access. Customers bring authorized credentials or use hosted routing for TEKIZ.AI account control.

Choose routed models from one Aider setup

Aider stays pointed at one address while TEKIZ.AI chooses a provider, uses local models when preferred, and switches to a backup when needed.

Next steps

Create an API key, open the Aider guide, copy the hosted quickstart, or estimate routing fit.