GitHub Copilot
Configure GitHub Copilot for your enterprise and verify the request in your console logs.
Configuration
Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model
- Run Chat: Manage Language Models in VS Code and add a Custom Endpoint provider. Managed accounts may need an administrator to enable the relevant BYOK policy.
- Select Chat Completions, enter the full URL ending in /v1/chat/completions, and supply the project key and allowed model ID.
| API protocol | Address to enter |
|---|---|
| Chat Completions | Full URLhttps://tokenpyxis.com/v1/chat/completions |
Verification
Select the added model from the VS Code Chat model picker and verify it with a short message.
Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps
Troubleshooting
If the model is missing, check the VS Code version, model visibility and organization policy. This setup covers model selection in VS Code Chat. Verify other Copilot features in their own surfaces.
