Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click the GitHub Copilot tile
Click Connect and complete the OAuth flow in your browser
Test the connection — kRouter auto-refreshes tokens from here on
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
gh/gpt-5.4How GitHub Copilot billing works with kRouter
GitHub Copilot connects with your existing subscription — kRouter signs in with OAuth and reuses the plan you already pay for, so there is no per-token bill. kRouter authenticates it via oauth. 26 models are routable as gh/<model>.
Through kRouter, GitHub Copilot serves chat and code completion and embeddings, exposed on /v1/embeddings. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from GitHub Copilot is a one-line model change in your client rather than a rewrite.
GitHub Copilot models & pricing
Prices are USD per 1M tokens, cheapest first. You are not billed per token on this provider — the figures show what the same model costs elsewhere, which is what routing here saves you.
| Model | Route as | Input /1M | Output /1M |
|---|---|---|---|
| GPT-4o mini | gh/gpt-4o-mini | $0.15 | $0.60 |
| GPT-3.5 Turbo | gh/gpt-3.5-turbo | $0.50 | $1.50 |
| Grok Code Fast 1 | gh/grok-code-fast-1 | $0.50 | $2.00 |
| Claude Haiku 4.5 | gh/claude-haiku-4.5 | $0.50 | $2.50 |
| Gemini 3 Flash | gh/gemini-3-flash-preview | $0.50 | $3.00 |
| Gemini 3.1 Pro | gh/gemini-3.1-pro-preview | $0.50 | $3.00 |
| GPT-5 Mini | gh/gpt-5-mini | $0.75 | $3.00 |
| Raptor Mini | gh/oswe-vscode-prime | $1.00 | $4.00 |
| GPT-4 | gh/gpt-4 | $2.50 | $10.00 |
| GPT-4o | gh/gpt-4o | $2.50 | $10.00 |
| GPT-4.1 | gh/gpt-4.1 | $2.50 | $10.00 |
| Gemini 2.5 Pro | gh/gemini-2.5-pro | $2.00 | $12.00 |
| GPT-5.4 | gh/gpt-5.4 | $3.00 | $12.00 |
| GPT-5.4 Mini | gh/gpt-5.4-mini | $3.00 | $12.00 |
| Claude Sonnet 4 | gh/claude-sonnet-4 | $3.00 | $15.00 |
| Claude Sonnet 4.5 | gh/claude-sonnet-4.5 | $3.00 | $15.00 |
| Claude Sonnet 4.6 | gh/claude-sonnet-4.6 | $3.00 | $15.00 |
| GPT-5.2 | gh/gpt-5.2 | $5.00 | $20.00 |
| GPT-5.2 Codex | gh/gpt-5.2-codex | $5.00 | $20.00 |
| Claude Opus 4.5 | gh/claude-opus-4.5 | $5.00 | $25.00 |
| Claude Opus 4.6 | gh/claude-opus-4.6 | $5.00 | $25.00 |
| Claude Opus 4.7 | gh/claude-opus-4.7 | $5.00 | $25.00 |
| GPT-5.3 Codex | gh/gpt-5.3-codex | $6.00 | $24.00 |
| GoldenEye | gh/goldeneye-free-auto | — | — |
| Text Embedding 3 Small (GitHub) | gh/text-embedding-3-small | — | — |
| Text Embedding 3 Large (GitHub) | gh/text-embedding-3-large | — | — |
GitHub Copilot links
GitHub Copilot FAQ
Is GitHub Copilot free through kRouter?
GitHub Copilot does not bill per token here — kRouter uses your existing subscription via OAuth, so the only cost is whatever you already pay GitHub Copilot directly. kRouter itself is MIT-licensed and free.
How do I use GitHub Copilot with Claude Code or Cursor?
Connect GitHub Copilot in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as gh/<model>.
Which GitHub Copilot models can kRouter route to?
26 models, including GPT-3.5 Turbo, GPT-4, GPT-4o. Every one is addressed as gh/<model> from any client.
What happens when GitHub Copilot is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.