smallmain/vscode-unify-chat-provider

Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X Premium+) account quotas.

What it solves

Unify Chat Provider is a VS Code extension that allows users to integrate multiple LLM API providers into the native GitHub Copilot Chat interface. It removes the limitation of using only Copilot's default models by enabling the use of any LLM via the VS Code Language Model API.

How it works

The extension acts as a bridge between the VS Code Language Model API and various external LLM providers. It supports multiple API formats (OpenAI, Anthropic, Gemini, Ollama) and provides a visual interface for managing providers and models. It also integrates with the VS Code Source Control view to provide enhanced commit message generation.

Who it’s for

Developers who use VS Code and want to use their preferred LLM (such as Claude, DeepSeek, or local models via Ollama) directly within the Copilot Chat UI without switching windows or using separate extensions for each provider.

Highlights

  • Broad Provider Support: Adapts to 45+ mainstream providers and 200+ models with built-in recommended parameters.
  • Flexible Configuration: Offers one-click configuration for well-known providers, manual setup, and migration from other apps/extensions.
  • Code Completion: Provides high-performance FIM (Fill-In-the-Middle) and Next Edit Prediction code completion using various algorithms (Simple, Zed, Inception, Mistral).
  • Account Quota Integration: Allows one-click use of existing account quotas from services like Claude Code, Gemini CLI, and xAI Grok.
  • Balance Monitoring: Built-in tools to monitor API balances for providers like DeepSeek, OpenRouter, and SiliconFlow.

Related

  • Project
    VicBilibily/GCMP

    GCMP is a VS Code extension that integrates dozens of Chinese LLM providers (ZhipuAI, MiniMax, DeepSeek, Alibaba Bailian, Tencent Hunyuan, etc.) plus OpenAI‑compatible APIs. It lets you select a provider, store its API key, and assign different models to specific assistant tasks (utility work, inline chat, commit‑message generation, vision, agents). The extension shows quota/balance in the status bar, supports per‑provider retry/ratelimit settings, proxy/TLS configuration, and optional HAR debugging. Ideal for developers in China who want to use local cloud LLMs instead of Copilot’s default model.

  • Project
    iimeta/fastapi

    An enterprise-grade LLM API integration system that provides a unified, OpenAI-compatible interface to access multiple AI model providers.

  • Project
    huggingface/llm-vscode

    A VS Code extension that provides AI-powered ghost-text code completion and code attribution using various LLM backends like Hugging Face and Ollama.

  • Project
    bernardo-bruning/ollama-copilot

    Ollama Copilot is a Go‑based proxy that lets you use any Ollama‑compatible (or other) LLM as a drop‑in replacement for GitHub Copilot, enabling local code completions in VS Code, Neovim, Zed, PyCharm, Emacs, etc.

  • Project
    sublimelsp/LSP-copilot

    A Sublime Text plugin that integrates GitHub Copilot via a language server to provide AI-powered code completions and chat.