Coding-agent toolkit Pi (v0.99.1, 2026-09-29) adds gpt-6.1-sol to OpenAI, Azure OpenAI Responses, and OpenAI Codex providers, makes GPT-6.1 Sol the default OpenAI Codex model, and fixes bundled /login failing with a missing openai-chatgpt.js module. 5 commits ahead of v0.99.0. Model docs: models.md.

Key Takeaways

  • ✓Release v0.99.1; 5 commits ahead of v0.99.0
  • ✓OpenAI Codex default → GPT-6.1 Sol (gpt-6.1-sol); also on OpenAI + Azure OpenAI Responses
  • ✓Bundled /login missing openai-chatgpt.js fixed
  • ✓Docs: models.md; catalog https://pi.dev/models
  • ✓Upgrade to v0.99.1; verify with /model; pin via Ctrl+S
Pi 0.99.1: OpenAI Codex default model switches to GPT-6.1 Sol; bundled /login module fix
🖼️Official Media
Click to view high-res
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Background

CLI coding agents need GPT-6.1 Sol as the Codex default and a working bundled /login. Pi v0.99.1 ships both.

What shipped

v0.99.1: gpt-6.1-sol on OpenAI / Azure OpenAI Responses / OpenAI Codex; Codex default → Sol; fix missing openai-chatgpt.js in bundled /login. 5 commits ahead of v0.99.0.

Benchmarks

No SWE-bench numbers. Anchors: published 2026-09-29T18:27:00Z; ahead_by

  1. Measure your own Codex sessions after the default change.

Get started

Upgrade to v0.99.1; verify with /model; pin via Ctrl+S. Docs: https://github.com/earendil-works/pi/blob/v0.99.1/packages/coding-agent/docs/models.md

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextOpenAI Codex 0.159.1: GPT-6.1 Sol becomes default; Bedrock Mantle & Runtime catalogs updated
Read Now→