GitHub Copilot App Integration
Use Claude and GPT models in GitHub's Copilot desktop app through Halfbill. One custom provider entry, full cost tracking.
The GitHub Copilot app is GitHub's desktop app for agent-driven development — start agent sessions from issues, pull requests, or prompts, run parallel workflows in isolated workspaces, and merge PRs without leaving the app. It supports bring your own key (BYOK), so you can run agent sessions against your own model provider.
Add Halfbill as that provider and every session can use any Claude or GPT model in the catalog — with full cost visibility in your dashboard.
One provider entry. No config files. Works on any Copilot plan, or with no Copilot plan at all.
Using Halfbill Code? This integration also works with a Halfbill
Code plan key. Use the canonical model IDs from
the catalogue (for example claude-sonnet-5).
Setup
Sign Up for Halfbill
Sign up, then create an API key in the dashboard and copy it when shown (it starts with llmgtwy_).
Install the GitHub Copilot App
Download it from github.com/features/ai/github-app (macOS, Windows, or Linux) and sign in with your GitHub account.
Add Halfbill as a Model Provider
In the app, open Settings → Model Providers, select Add provider, and choose the OpenAI-compatible provider type. Set the Base URL to:
https://api.halfbill.uk/v1Paste your Halfbill API key and save. The key is stored in your OS keychain.
Start a Session with Any Model
Halfbill's models now appear in the model picker alongside Copilot-hosted models. Choose one when you start an agent session — each session can use a different model.
Why This Works
Halfbill's /v1 endpoint is OpenAI-compatible. The Copilot app fetches the model list from Halfbill and routes each agent session through it. This means:
- Use Claude and GPT — every model in the catalog supports tool calling and streaming
- Keep your workflow — sessions, workspaces, and PR merging work exactly the same
- Track costs — every request appears in your Halfbill dashboard
- Automatic caching — repeated requests hit cache, saving money
Choosing Models
All models available to your account show up in the app's model picker; agent sessions work with models that support tool calling and streaming. Browse the models page to compare capabilities and pricing.
Reasoning Effort Levels
The Copilot app discovers only model IDs from a BYOK provider — it cannot learn which reasoning effort levels a model supports, so the composer's reasoning control stays on the app default (Medium) and any level you pick reverts until you configure the model:
- In the app, open Settings → Model Providers and select your Halfbill provider
- Edit the model and set its supported reasoning effort levels (available since app v1.1.8)
Enter only levels the model actually supports: Halfbill forwards your selection upstream as-is, and unsupported levels are rejected. To find the right values for a model, open it on the models page and check the Reasoning Efforts badges, or query the API — each entry in GET https://api.halfbill.uk/v1/models lists them under providers[].reasoning_efforts.
While unconfigured, sessions still work: the app sends no reasoning effort and the model uses its default.
Good to Know
- Keys stay local — the app stores your API key in the OS keychain and never reads it back into the UI.
- Any plan works — BYOK providers work on every Copilot plan, including Free. You don't need a paid Copilot subscription to run agent sessions through Halfbill.
- Business and Enterprise — adding model providers is gated by the Enable custom models (BYOK) policy, which your admin must turn on. Accessing the Copilot app itself also requires the Copilot CLI enabled in policy settings.
- Agent sessions only — BYOK covers the app's model-powered agent sessions. Inline code completions in your editor still use Copilot's own service.
GitHub Copilot in VS Code
Copilot Chat in VS Code supports custom endpoints too:
- Run Chat: Manage Language Models from the Command Palette
- Choose Add Models → Custom Endpoint, enter your Halfbill API key, and select Chat Completions as the API type (Halfbill is OpenAI-compatible)
- In the generated
chatLanguageModels.json, point the modelurlathttps://api.halfbill.uk/v1/chat/completionsand set the modelidfrom the models page
Your Halfbill models then appear in the VS Code chat model picker.
Troubleshooting
Models don't appear in the picker
- Verify the Base URL is exactly
https://api.halfbill.uk/v1(note the/v1at the end) - Check your API key starts with
llmgtwy_and is active in your dashboard
401 Unauthorized
Your API key is invalid or was revoked. Generate a new key in the dashboard and update the provider entry in Settings → Model Providers.
402 or credit errors
Your Halfbill organization is out of credits. Top up in the dashboard — BYOK sessions bill through Halfbill, not Copilot premium requests.
Reasoning effort resets to Medium
The app can't discover reasoning support from a BYOK provider, so the control reverts until you set the model's supported levels by hand — see Reasoning Effort Levels.
Provider option is missing
BYOK in the Copilot app shipped in June 2026 — update to the latest app version. On Business or Enterprise plans, ask your admin to enable the Enable custom models (BYOK) policy — and the Copilot CLI policy if you can't access the app at all.
View all available models on the models page.
Need help? Email support@halfbill.uk.
How is this guide?