OAI Compatible Provider for Copilot installs statistics

<div align="center"> <img src="https://github.com/JohnnyZ93/oai-compatible-copilot/raw/HEAD/assets/logo.png" alt="OAICopilot Logo" width="120" height="120">

OAI Compatible Provider for Copilot

A VSCode extension to use OpenAI/Ollama/Anthropic/Gemini API Providers in GitHub Copilot Chat 🔥

English | 简体中文

</div>

✨ Features

• Multi-API support: OpenAI/Ollama/Anthropic/Gemini APIs (ModelScope, SiliconFlow, DeepSeek...)
• Vision models: Full support for image understanding capabilities
• Advanced configuration: Flexible chat request options with thinking/reasoning control
• Multi-provider management: Configure models from multiple providers simultaneously with automatic API key management
• Multi-config per model: Define different settings for the same model (e.g., GLM-4.6 with/without thinking)
• Visual configuration UI: Intuitive interface for managing providers and models
• Auto-retry: Handles API errors (429, 500, 502, 503, 504) with exponential backoff
• Token usage: Real-time token counting and provider API key management from status bar
• Git integration: Generate commit messages directly from source control
• Import/export: Easily share and backup configurations
• Tools optimization: Optimize agent read_file tool handling, avoid to read small chunks for large file.

Requirements

• VS Code 1.104.0 or higher.
• OpenAI-compatible provider API key.

⚡ Quick Start

1. Install the OAI Compatible Provider for Copilot extension here.
2. Open VS Code Settings and configure oaicopilot.baseUrl and oaicopilot.models.
3. Open GitHub Copilot Chat interface.
4. Click the model picker and select "Manage Models...".
5. Choose "OAI Compatible" provider.
6. Enter your API key — it will be saved locally.
7. Select the models you want to add to the model picker.

Settings Example

"oaicopilot.baseUrl": "https://api-inference.modelscope.cn/v1",
"oaicopilot.models": [
    {
        "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
        "owned_by": "modelscope",
        "context_length": 256000,
        "max_tokens": 8192,
        "temperature": 0,
        "top_p": 1
    }
]

✨ Configuration UI

The extension provides a visual configuration interface that makes it easy to manage global settings, providers, and models without editing JSON files manually.

Opening the Configuration UI

There are two ways to open the configuration interface:

1. From the Command Palette:

   • Press Ctrl+Shift+P (or Cmd+Shift+P on macOS)
   • Search for "OAICopilot: Open Configuration UI"
   • Select the command to open the configuration panel

2. From the Status Bar:

   • Click on the "OAICopilot" status bar item in the bottom-right corner of VS Code

<details> <summary>Click Here for Details</summary>

Workflow Example

1. Add a Provider:

   • Click "Add Provider" in the Provider Management section
   • Enter Provider ID: "modelscope"
   • Enter Base URL: "https://api-inference.modelscope.cn/v1"
   • Enter API Key: Your ModelScope API key
   • Select API Mode: "openai"
   • Click "Save"

2. Add a Model:

   • Click "Add Model" in the Model Management section
   • Select Provider: "modelscope"
   • Enter Model ID: "Qwen/Qwen3-Coder-480B-A35B-Instruct"
   • Configure basic parameters (context length, max tokens, etc.)
   • Click "Save Model"

3. Use the Model in VS Code:

   • Open GitHub Copilot Chat (Ctrl+Shift+I or Cmd+Shift+I)
   • Click the model picker in the chat input
   • Select "Manage Models..."
   • Choose "OAI Compatible" provider
   • Select your configured models
   • Start chatting with the model!

Tips & Best Practices

• Important: If you use the configuration UI, the global baseURL and API key become invalid.
• Provider IDs: Use descriptive names that match the service (e.g., "modelscope", "iflow", "anthropic")
• Model IDs: Use the exact model identifier from the provider's documentation
• Config IDs: Use meaningful names like "thinking", "no-thinking", "fast", "accurate" for multiple configurations
• Base URL Overrides: Set model-specific base URLs when using models from different endpoints of the same provider
• Save Frequently: Changes are saved to VS Code settings immediately
• Refresh: Use the "Refresh" buttons to reload current configuration from VS Code settings

Model family & System Prompts

VS Code Copilot has optimized system prompts for specific models. Detailed introduction

Below are the model family settings supported by Copilot:

Model Family	General family	Specific Model family	Notes
Anthropic	'claude', 'Anthropic'	'claude-sonnet-4-5', 'claude-haiku-4-5'
Gemini	'gemini'	'gemini-3-flash'	"github.copilot.chat.alternateGeminiModelFPrompt.enabled": true
xAI	'grok-code'
OpenAI	'gpt', 'o4-mini', 'o3-mini', 'OpenAI'	'gpt-4.1', 'gpt-5-codex', 'gpt-5', 'gpt-5-mini', !!family.startsWith('gpt-') && family.includes('-codex'), !!family.match(/^gpt-5\.\d+/i)	"github.copilot.chat.alternateGptPrompt.enabled": true

</details>

✨ Multi-API Mode

The extension supports five different API protocols to work with various model providers. You can specify which API mode to use for each model via the apiMode parameter.

Supported API Modes…