Skip to main content
FireConnect routes Pi through Fireworks AI models. See the FireConnect overview for install and CLI basics.

​
Prerequisites

​
Enable Fireworks routing

fireconnect login
fireconnect pi on
Restart Pi after enabling if it is already running. 
fireconnect pi status

​
Using Fire Pass

Use your fpk_... key during login or with --api-key: 
fireconnect pi on --api-key fpk_...
FireConnect detects Fire Pass keys and defaults Pi to glm-fast-latest.

​
Default model

Pi routes a single default model. The default is glm-fast-latest.

​
What gets written

FireConnect:
  • Sets defaultProvider / defaultModel in ~/.pi/agent/settings.json
  • Stores the API key in ~/.pi/agent/auth.json ($FIREWORKS_API_KEY when from env, literal with --api-key; never a literal in keychain mode)
  • Writes auth.json at mode 0600
FireConnect snapshots both files under ~/.fireconnect/pi/ before the first change. Running fireconnect pi off restores them byte-for-byte.

​
API key handling

  • If the key comes from the OS keychain, it is written as $FIREWORKS_API_KEY so the secret stays out of settings
  • Keychain mode installs a shell profile hook so Pi can read FIREWORKS_API_KEY at launch
  • Passing --api-key writes the literal key to auth.json instead

​
Browsing and picking models

fireconnect pi model list              # browse serverless endpoints
fireconnect pi model select            # pick Pi's default model
fireconnect pi model select --search glm
Fire Pass keys (fpk_...) show Fire Pass-supported routers only.

​
FireRouter mode

fireconnect pi on --router overrides Pi’s built-in Anthropic provider so its existing Claude model catalog is sent through https://router.fireworks.ai/v1. The Fireworks key is supplied through X-FireRouter-Fireworks-Key; an Anthropic API key is also required: 
fireconnect pi on --router --anthropic-api-key sk-ant-...
fireconnect pi on --router
# Then choose an Anthropic model inside Pi with /model.
You can switch among Anthropic models inside Pi without re-running FireConnect. FireConnect backs up settings.json, auth.json, and models.json, and fireconnect pi off restores all three byte-for-byte. model select and model reset do not apply in router mode.
In router mode, Pi’s /model picker still shows Anthropic’s built-in model names (for example, Claude Sonnet 4.5). The selected name is passed through FireRouter, but the display label is Pi’s own — it does not reflect the Fireworks model actually serving the request behind the router. Use fireconnect pi status to see the underlying routing.

​
CLI reference

fireconnect pi on              # Enable Fireworks routing
fireconnect pi off             # Restore original settings and auth
fireconnect pi status          # Check current provider and model
fireconnect pi model list      # Browse serverless endpoints
fireconnect pi model select    # Pick a model interactively
fireconnect pi model reset     # Reset model to default
fireconnect pi help            # Show harness-specific help
Run fireconnect pi help for all options.

​
Switch models

fireconnect pi on --main glm-5p1
fireconnect pi on --router     # route Anthropic models through FireRouter

​
Turn off Fireworks routing

fireconnect pi off
This restores your previous settings.json and auth.json from the backup in ~/.fireconnect/pi/.

​
Use a non-default settings file

fireconnect pi on --settings-path /path/to/settings.json

​
Fireworks on Microsoft Foundry

Pi supports Fireworks on Microsoft Foundry (CLI: --provider azure or on --azure). See the FireConnect overview and Microsoft Foundry integration guide for portal setup.

​
Configure and enable

export AZURE_API_KEY=<your-azure-api-key>

fireconnect configure \
  --provider azure \
  --base-url https://<resource>.services.ai.azure.com \
  --api-key $AZURE_API_KEY

fireconnect pi on --main FW-GLM-5.1
One-off routing: 
fireconnect pi on --azure --base-url https://<resource>.services.ai.azure.com --main FW-MiniMax-M2.5

​
What gets written

FireConnect registers a fireworks-azure openai-completions provider in Pi’s models.json (labeled Fireworks on Microsoft Foundry) and sets defaultProvider / defaultModel in settings.json. The Azure API key is stored in auth.json as $AZURE_API_KEY when from the environment, or literally with --api-key. Pass your Foundry deployment name with --main. model list and model select browse the Fireworks serverless catalog only.

​
Turn off Foundry routing

To switch back to the Fireworks gateway: 
fireconnect configure --provider fireworks
fireconnect pi on
To remove FireConnect entirely and restore your original settings.json, auth.json, and models.json: 
fireconnect pi off
Restart Pi after switching or running off. See Turn off Foundry routing for details on global config behavior and uninstall.

​
Source

FireConnect is open source: github.com/fw-ai/fireconnect