Run Pi on GPT Realtime 2

by pi.devCoding agentpi.dev

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.

Run

Pionin

Launch Pi on GPT Realtime 2

Set up with agents

Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.

Get your API key

Where you can run it

GPT Realtime 2 runs on the routes below. Route only to EU providers when your data has to stay in Europe.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
OpenAI	US		No	$4.00	$24.00	$0.40

The model

GPT Realtime 2 by OpenAI: realtime voice model with GPT-5-class reasoning, vision input and configurable reasoning effort.

Available on

Pricing from$4.00/ 1M input$24.00/ 1M output$0.40/ 1M cache read128Kcontext

Privacy

ZDR
Training: No
Region: US

More apps on Opper

Claude Code

Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.

Codingopper launch claude

Codex

OpenAI's open-source coding CLI. Run it on any model on Opper.

Codingopper launch codex

DeepSeek Harness

DeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.

CodingOpenAI-compatible