~/.pi/agent/models.json that points at Chat Completions on POST /v1/chat/completions.
This page covers LLM text only (
https://llm.modellix.ai). For Pi media packages and skills (image, video, speech), see Plugin and Skill.Modellix model IDs are provider/name (for example openai/gpt-5.5). Put that full string in each model id under your custom provider. See Models & Pricing.Set Up Pi
1
Get a Modellix API Key
Create a Modellix API key in the console and export it so Add the same line to your shell profile (for example
models.json can resolve $MODELLIX_API_KEY:~/.zshrc) for persistent use.2
Add a Custom Provider
Create or update Merge the
~/.pi/agent/models.json:modellix entry into an existing providers object if you already use custom models. Add or remove entries under models as needed.3
Select a Modellix Model
In an interactive Pi session, run Pi reloads
/model and choose a Modellix entry (for example openai/gpt-5.5 under the modellix provider).Or start Pi with the provider and model on the command line:models.json each time you open /model, so you can edit the file during a session without restarting.4
Start Pi
Start Pi as usual:Or with Modellix selected up front:
Troubleshooting
Related
- Pi Custom Models โ
models.jsonschema and examples - Pi Providers โ auth and custom providers overview
- Models & Pricing โ Model IDs and rates
- LLM API guide โ protocols and curl examples
- OpenClaw ยท OpenCode โ other OpenAI-compatible custom setups
- Plugin ยท Skill โ Pi media capabilities