Pi is a lightweight open coding agent from pi.dev. It's a simple, fast terminal agent that edits code and runs tasks from natural-language prompts, built to stay minimal and model-agnostic rather than locked to one provider. On Opper, launch it on any of 700+ models, fall back across providers automatically, and keep everything on one key.
PioninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Qwen3 VL 235B A22B Instruct runs on the routes below. Route only to EU providers when your data has to stay in Europe. Its route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | ||
|---|---|---|---|---|---|---|---|---|
| US | No | $0.20 | $0.88 | $0.11 |
Qwen3 VL 235B A22B Instruct by Alibaba, an open-weight vision-language model with 235B parameters, 22B active, and 131K context.
Step-by-step setup for running Pi on each of these models through Opper.
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claude
OpenAI's open-source coding CLI. Run it on any model on Opper.
opper launch codex
DeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.
OpenAI-compatible