Skip to main content
FireConnect adds Fireworks AI models to GitHub Copilot Chat in Visual Studio Code by writing a custom language-model endpoint. See the FireConnect overview for install and CLI basics.

Manual setup (GitHub Copilot)

Step-by-step UI walkthrough with screenshots — add a Fireworks custom endpoint without the FireConnect CLI

​
Prerequisites

VS Code supports direct Fireworks routing only. Fireworks on Microsoft Foundry is not available for Copilot custom endpoints.

​
Enable Fireworks routing

VS Code stores custom-endpoint API keys (encrypted) in state.vscdb. Quit VS Code before running on or off — FireConnect hard-errors if VS Code is still running unless you pass --force. 
export FIREWORKS_API_KEY=fw_...
fireconnect vscode on
Or pass the key once: 
fireconnect vscode on --api-key fw_...
Start or restart VS Code, then open Copilot Chat and pick a Fireworks model from the model picker. 
fireconnect vscode status   # read-only — works while VS Code is running

​
Browse and add models

model list, model add, model select, and model reset only edit chatLanguageModels.json. VS Code hot-reloads that file — no restart needed for model changes. 
fireconnect vscode model list              # browse serverless endpoints
fireconnect vscode model list --search glm
fireconnect vscode model add glm-latest
fireconnect vscode model add deepseek-v4-pro
fireconnect vscode model select            # pick a model to add interactively
Short model IDs are expanded to full Fireworks paths. FireConnect writes model metadata (display name, token limits, tool calling, and vision flags) into your Copilot language-model config. In Copilot Chat, open the model picker (Auto), expand Other Models, and choose your model under Fireworks.

​
What gets written

FireConnect merges a Fireworks custom endpoint into VS Code’s language-model config and stores the API key in VS Code’s secret storage:
WhatWhere
Provider + modelschatLanguageModels.json
Encrypted API keystate.vscdb (ItemTable, key secret://chat.lm.secret.fw-...)
Platform paths:
PlatformchatLanguageModels.jsonstate.vscdb
Linux~/.config/Code/User/chatLanguageModels.json~/.config/Code/User/globalStorage/state.vscdb
macOS~/Library/Application Support/Code/User/chatLanguageModels.json~/Library/Application Support/Code/User/globalStorage/state.vscdb
Windows%APPDATA%\Code\User\chatLanguageModels.json%APPDATA%\Code\User\globalStorage\state.vscdb
The endpoint uses model URL https://api.fireworks.ai/inference (VS Code appends /v1/chat/completions). FireConnect snapshots the original chatLanguageModels.json under ~/.fireconnect/vscode/ before the first change. Running fireconnect vscode off restores it and removes the encrypted key from state.vscdb.

​
CLI reference

fireconnect vscode on              # Add the Fireworks provider (quit VS Code first)
fireconnect vscode off             # Restore config and remove the stored key
fireconnect vscode status          # Show provider, auth, and registered models
fireconnect vscode model list      # Browse serverless endpoints
fireconnect vscode model add <id>  # Add a model (hot-reloads)
fireconnect vscode model select    # Pick a model to add interactively
fireconnect vscode model reset     # Reset fireconnect-managed models to default
fireconnect vscode help            # Show harness-specific help
Run fireconnect vscode help for all options, including --vscode-path (explicit chatLanguageModels.json path) and --force.

​
Turn off Fireworks routing

Quit VS Code, then run: 
fireconnect vscode off
This restores your previous chatLanguageModels.json from the backup in ~/.fireconnect/vscode/ and removes the FireConnect secret from state.vscdb. Restart VS Code for the change to take effect.

​
Source

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