@pi-plugins/fast-mode
Fast service-tier extension for pi-agent.
Package details
Install @pi-plugins/fast-mode from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:@pi-plugins/fast-mode- Package
@pi-plugins/fast-mode- Version
0.1.12- Published
- Sep 14, 2026
- Downloads
- 1,127/mo · 380/wk
- Author
- kedom1337
- License
- MIT
- Types
- extension
- Size
- 3.5 MB
- Dependencies
- 0 dependencies · 2 peers
Pi manifest JSON
{
"extensions": [
"./dist/index.mjs"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
@pi-plugins/fast-mode
Request priority inference for selected models in pi with a session toggle.
Install
pi install npm:@pi-plugins/fast-mode
To try it for one session without changing your settings:
pi -e npm:@pi-plugins/fast-mode
Usage
Use /fast to control fast mode for the current session:
| Command | Action |
|---|---|
/fast |
Toggle fast mode. |
/fast on |
Enable fast mode. |
/fast off |
Disable fast mode. |
/fast status |
Show the current state and explain whether it applies to the selected model. |
To start a session with fast mode enabled:
pi --fast
Fast mode applies only to models listed in the configuration. Other models are left
unchanged. A [fast mode] indicator appears above the editor while active.
Supported providers
| Provider | Pi provider |
|---|---|
| OpenAI | openai |
| OpenAI Codex | openai-codex |
Priority availability depends on the provider and model.
Configuration
Optionally create <agent-dir>/extensions/fast-mode.json, typically
~/.pi/agent/extensions/fast-mode.json. The defaults are:
{
"enabled": false,
"models": [
"openai/gpt-5.4",
"openai/gpt-5.5",
"openai/gpt-5.6-sol",
"openai/gpt-5.6-terra",
"openai/gpt-5.6-luna",
"openai/gpt-6-astra",
"openai-codex/gpt-5.4",
"openai-codex/gpt-5.5",
"openai-codex/gpt-5.6-sol",
"openai-codex/gpt-5.6-terra",
"openai-codex/gpt-5.6-luna",
"openai-codex/gpt-6-astra"
],
"showStatus": true
}
| Setting | Description |
|---|---|
enabled |
Enable fast mode at session start. /fast changes only the current session and does not write to the file. |
models |
The exact provider/model-id pairs fast mode applies to. |
showStatus |
Show the status indicator while fast mode is active. |
Notes
Priority inference can cost more. Check your provider's pricing before enabling it.