> ## 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

> Configure GitHub Copilot Chat to call Fireworks AI open-weight models through a custom endpoint, with step-by-step setup for the Copilot model picker.

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).

> [card] [Nexus CLI (recommended)](https://fireworks.ai/docs/nexus/harnesses/vscode.md)
>
> Automate VS Code setup with `nexus vscode`. It writes `chatLanguageModels.json`, stores your API key, and adds the Fireworks model catalog, starting on `auto`.

The steps below are for **manual setup** through the Copilot Chat UI (no Nexus CLI).

> [!NOTE]
>
> 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

**1. Open model settings**

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](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-1-open-settings.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=7dda5b04a5431d90902cc403e36e7aa9)

**2. Add a custom endpoint**

In **Language Models**, click **+ Add Models...** in the top right, then choose **Custom Endpoint**.

![Add Models menu with Custom Endpoint selected](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-2-custom-endpoint.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=441264a0e9ad0ebc19e9289b62e374a0)

**3. Name the endpoint group**

Enter **Fireworks AI** as the group name and press Enter.

![Prompt to enter group name Fireworks AI](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-3-name-endpoint.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=2cf0531d37c72be697d20df46dcb05e4)

**4. Enter your API key**

Paste your Fireworks API key (hidden by default) and press Enter to confirm.

![Fireworks API key entry field](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-4-api-key.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=813455e10c6e79c315e26005575f2c79)

**5. Choose Responses API**

When asked for the default request/response format, select **Responses API**.

![API type selection with Responses API highlighted](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-5-api-type.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=707ea7141c6ede985b036139c49bedc7)

**6. Configure the model template**

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](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-6-config-template.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=c4ca19b97622d6ab88ef05d2f21315a9)

**7. Add model details and save**

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](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-7-model-details.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=b78270fead6c63eb72c1b10f41c204d1)

> [!WARNING]
>
> 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.

**8. Select your model in chat**

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](https://mintcdn.com/fireworksai-docs/og0-IUNdDqdAnszP/images/integrations/github-copilot/step-8-select-model.png?fit=max\&auto=format\&n=og0-IUNdDqdAnszP\&q=85\&s=2fd8f6e7a64c501c9b0c689ab87c4d40)

## Related

* [Nexus CLI for VS Code](https://fireworks.ai/docs/nexus/harnesses/vscode.md): automate custom-endpoint setup from the terminal
* [Nexus CLI overview](https://fireworks.ai/docs/nexus/cli.md): install once, route multiple harnesses through Fireworks
* [Claude Code](https://fireworks.ai/docs/nexus/harnesses/claude-code.md): use Fireworks models with Claude Code
* [Development Setup with Fireworks Docs MCP](https://fireworks.ai/docs/ecosystem/integrations/development-setup.md): add Fireworks docs to your coding agent


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.