// IDE Plugin
Use GitHub Copilot Chat with llmrelay
Route Copilot Chat away from GitHub's default model. Point it at api.llmrelay.dev and get the same models at half the price.
Recommended model
claude-sonnet-4-6
Route
openai-compatible
On llmrelay
$1.5/M · $7.5/M
Setup
- 1 Install the Copilot Chat extension.
- 2 Install "Copilot Chat: Custom Endpoint" or use a proxy like litellm.
- 3 Point the OpenAI base URL to https://api.llmrelay.dev/v1.
- 4 Use claude-sonnet-4-6 or claude-opus-4-7 in the model picker.
Config
# via litellm proxy config
model_list:
- model_name: gpt-4o
litellm_params:
model: openai/claude-sonnet-4-6
api_key: sk-llmrelay-...
api_base: https://api.llmrelay.dev/v1 Smoke test
Copy, paste, run. If you get JSON back with a message, you're good.
Open Copilot Chat → "explain this function"
Gotchas
- !GitHub does not officially support custom endpoints; a proxy layer (litellm, one-api, LiteLLM Router) is standard.
You need an llmrelay key first
Sign up in about 30 seconds. New accounts get $0.20 in free credit — enough to smoke-test every model.