Ollama Cloud for GitHub Copilot Chat

Use hosted Ollama Cloud models directly from the GitHub Copilot Chat model picker in Visual Studio Code—without installing Ollama or running a local model server.

This extension is a native VS Code LanguageModelChatProvider. It validates an Ollama API key, discovers the hosted models available to your account, and streams responses directly from ollama.com into Copilot Chat without a local proxy.

Highlights

• Direct Ollama Cloud integration with no Ollama app, CLI, or local models
• API keys stored in VS Code Secret Storage
• Live model discovery enriched with context length, modality, and tool metadata
• Streaming text and separate thinking parts
• Model-specific thinking effort in the Copilot Chat model picker
• Image inputs and agent-mode tool calls where supported
• Exact response token accounting for Copilot's context indicator
• Status-bar indicator for five-hour and weekly subscription usage

Quick start

1. Install Ollama Cloud for GitHub Copilot Chat. You need VS Code 1.125 or newer, GitHub Copilot Chat, and an Ollama account with Cloud API access.
2. Create a key in Ollama API keys.
3. Run Ollama Cloud: Configure API Key from the Command Palette.
4. Open Copilot Chat, select Manage Models, enable Ollama Cloud, then choose a hosted model.

Click the Ollama status-bar item or run Ollama Cloud: Show Subscription Usage to inspect exact five-hour and weekly utilization, per-model request counts, and tokens observed by this extension. Ollama's account limits are GPU/time based rather than token quotas, so account utilization and local token totals are shown separately.

Use Ollama Cloud: Manage Connection to test inference, refresh models, replace or remove the key, inspect usage and logs, or create a secret-safe diagnostic snapshot.

Documentation

• Setup, commands, settings, and troubleshooting
• Models, capabilities, thinking, and accounting
• API key and security model
• Development and releases

Related projects

• Grok for GitHub Copilot Chat — Use xAI Grok models directly from the Copilot Chat model picker.
• Codex Bridge for Copilot Chat — Use OpenAI Codex models with a ChatGPT Plus or Pro subscription.
• Poolside for GitHub Copilot Chat — Use hosted Poolside coding models directly from Copilot Chat.

Unofficial project; not affiliated with Ollama, GitHub, or Microsoft. Ollama account limits and charges still apply. Licensed under MIT.