@gowthamgts/pi-codex-fast-mode

A pi extension for toggling fast mode on supported OpenAI Codex models.

Packages

Package details

extension

Install @gowthamgts/pi-codex-fast-mode from npm and Pi will load the resources declared by the package manifest.

npm repo home report

$ pi install npm:@gowthamgts/pi-codex-fast-mode

Package: @gowthamgts/pi-codex-fast-mode
Version: 1.0.1
Published: Aug 12, 2026
Downloads: 112/mo · 14/wk
Author: gowthamgts
License: MIT
Types: extension
Size: 7.5 KB
Dependencies: 0 dependencies · 1 peer

Pi manifest JSON

{
  "extensions": [
    "./index.ts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

pi-codex-fast-mode

A pi extension that enables Codex fast mode by default and lets you switch between fast and standard modes.

It adds service_tier: "priority" to provider requests for these openai-codex models:

gpt-5.4
gpt-5.5
gpt-5.6-luna
gpt-5.6-sol
gpt-5.6-terra

The extension deliberately leaves unsupported Codex models such as gpt-5.4-mini and gpt-5.3-codex-spark unchanged.

Controls

/fast on
/fast off
/fast status

Fast mode defaults to on in new sessions. The selected mode is stored in the current pi session and survives reloads and resumes. Supported models show ⚡ Codex fast or ○ Codex standard in pi's status bar.

Shared status key

The indicator is published under the CODEX_FOOTER_STATUS_KEY (codex-custom-footer) status slot, which the codex-usage extension inlines into its custom footer's stats line next to the remaining quota. Without that extension the status still appears on pi's default status line.

Install

From npm:

pi install npm:@gowthamgts/pi-codex-fast-mode

From this repository:

pi install ./extensions/codex-fast-mode

Or try it without installing:

pi -e ./extensions/codex-fast-mode/index.ts

Use the openai-codex provider with ChatGPT sign-in to get Codex's credit-based fast mode. Direct API-key usage applies API Priority processing and its separate token pricing instead.

Cost warning

Fast mode increases supported model speed by about 1.5x and consumes credits at a higher rate. As documented by OpenAI, GPT-5.5 and GPT-5.6 use 2.5x Standard credits, while GPT-5.4 uses 2x.

See OpenAI's speed documentation.

Development

From this extension's directory:

pnpm test
pnpm run check:load