> ## Documentation Index > Fetch the complete documentation index at: https://fireworks.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # GitHub Copilot > Use Fireworks AI models in GitHub Copilot Chat via a custom endpoint Use [Fireworks AI](https://fireworks.ai) models in **GitHub Copilot Chat** by adding a **Custom Endpoint** in VS Code (or other hosts that support Copilot custom models). Automate VS Code setup with `fireconnect vscode on`, which writes `chatLanguageModels.json`, stores your API key, and registers the preferred model catalog (v0.9.0+) The steps below are for **manual setup** through the Copilot Chat UI (no FireConnect CLI). Fireworks offers **200+ models**. Copy the model `id` and token limits from the [Model Library](https://app.fireworks.ai/models). Use endpoint URL `https://api.fireworks.ai/inference/v1`. ## Prerequisites * A Fireworks [API key](https://app.fireworks.ai/settings/users/api-keys) * GitHub Copilot with access to **Other Models** and **Custom Endpoint** (availability depends on your Copilot plan) ## Setup In Copilot Chat, click the active model name at the bottom (often **Auto**). In the menu, click the gear icon next to **Other Models**. Copilot Chat model picker with gear icon next to Other Models In **Language Models**, click **+ Add Models...** in the top right, then choose **Custom Endpoint**. Add Models menu with Custom Endpoint selected Enter **Fireworks AI** as the group name and press Enter. Prompt to enter group name Fireworks AI Paste your Fireworks API key (hidden by default) and press Enter to confirm. Fireworks API key entry field When asked for the default request/response format, select **Responses API**. API type selection with Responses API highlighted A configuration file opens. **Do not change** the auto-generated header at the top. Only fill in the model template below it. Copilot custom endpoint config file with template section Fill in your model fields, then save (**Ctrl+S** on Windows/Linux, **Cmd+S** on macOS) and close the settings modal. Example for [DeepSeek V4 Pro](https://app.fireworks.ai/models/fireworks/deepseek-v4-pro): | Field | Value | | ------------------- | ------------------------------------------- | | **id** | `accounts/fireworks/models/deepseek-v4-pro` | | **name** | `DeepSeek V4 Pro` | | **url** | `https://api.fireworks.ai/inference/v1` | | **toolCalling** | `true` | | **vision** | `false` | | **maxInputTokens** | `1000000` | | **maxOutputTokens** | `384000` | Completed model template with DeepSeek V4 Pro fields Use the exact model `id` and token limits from the model page in the [Model Library](https://app.fireworks.ai/models). Values differ per model. Return to Copilot Chat, open the model picker (**Auto**), expand **Other Models**, and choose your model under **Fireworks AI**. Model picker showing Fireworks AI custom model at bottom of Other Models ## Related * [FireConnect for VS Code](/docs/ecosystem/fireconnect/vscode): automate custom-endpoint setup from the terminal * [FireConnect overview](/docs/ecosystem/fireconnect/overview): install once, route multiple harnesses through Fireworks * [Claude Code](/docs/ecosystem/fireconnect/claude-code): use Fireworks models with Claude Code * [Development Setup with Fireworks Docs MCP](/docs/ecosystem/integrations/development-setup): add Fireworks docs to your coding agent