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.
Change models: quit VS Code → fireconnect vscode on --model <id>. See Models.

Manual setup (GitHub Copilot)

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

​
Prerequisites

​
Enable Fireworks routing

VS Code stores custom-endpoint API keys (encrypted) in state.vscdb. Quit VS Code before running on or off. In an interactive terminal, FireConnect waits for you to quit (or pass --force to write anyway).
Or pass the key once:
Start or restart VS Code, then open Copilot Chat and pick a Fireworks model from the model picker.

​
Browse and switch models

In v0.9.0, VS Code uses the Fireworks Responses API (apiType: responses). Kimi models support vision/image inputs; GLM models remain text-only.
on registers the preferred serverless catalog in the VS Code Chat model picker. Pick models under Other Models → Fireworks in Copilot Chat.

​
FireRouter

The Fireworks key stays encrypted in state.vscdb. An Anthropic BYOK key is optional for pass-through to Claude Opus 4.8.

​
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: Platform paths: The endpoint uses model URL https://api.fireworks.ai/inference (VS Code appends /v1/responses for the Responses API). The API key is not stored in the JSON. VS Code resolves the ${input:chat.lm.secret.<id>} reference through its secret storage. On macOS, safeStorage encrypts with a master key VS Code stores in the login Keychain. On Linux, safeStorage needs libsecret (secret-tool) for real encryption. Without it, Chromium falls back to a hardcoded password (obfuscated, not encrypted), which FireConnect still writes but warns about. FireConnect snapshots the original chatLanguageModels.json under ~/.fireconnect/vscode/ before the first change. Running fireconnect vscode off restores it byte-for-byte and deletes the chat.lm.secret.fw-* secret row from state.vscdb.

​
CLI reference

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:
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.

​
Fireworks on Microsoft Foundry

VS Code supports Fireworks on Microsoft Foundry (CLI: --provider azure or on --azure). See Microsoft Foundry in FireConnect and the portal setup guide.
Foundry routing requires a standard Azure API key. Fire Pass keys (fpk_...) are not supported. Quit VS Code before on or off.
One-off routing without changing global config:
Pass your Foundry model with --model (for example, FW-GLM-5.2), not a Fireworks serverless short ID. FireConnect adds a chat-completions custom endpoint pointed at Foundry and stores the Azure key in VS Code secret storage. fireconnect model list only browses the Fireworks serverless catalog on the direct gateway path. To switch back to the Fireworks gateway:
See Turn off Foundry routing for off and global config behavior.

​
Source

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