GitHub Copilot

See More

https://docs.github.com/en/copilot

tip

We support GitHub Copilot Chat API with automatic authentication handling

Property	Details
Description	GitHub Copilot Chat API provides access to GitHub's AI-powered coding assistant.
Provider Route on LiteLLM	github_copilot/
Supported Endpoints	/chat/completions, /responses, /embeddings, /v1/messages
API Reference	GitHub Copilot docs

Authentication

GitHub Copilot uses OAuth device flow for authentication. On first use, you'll be prompted to authenticate via GitHub:

1. LiteLLM will display a device code and verification URL
2. Visit the URL and enter the code to authenticate
3. Your credentials will be stored locally for future use

Usage - LiteLLM Python SDK

Chat Completion

GitHub Copilot Chat Completion

from litellm import completion

response = completion(
    model="github_copilot/gpt-5.2",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant"},
        {"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}
    ]
)
print(response)

GitHub Copilot Chat Completion - Streaming

from litellm import completion

stream = completion(
    model="github_copilot/gpt-5.2",
    messages=[{"role": "user", "content": "Explain async/await in Python"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

Responses

GPT Codex models such as gpt-5.3-codex only support the Responses API. Models that support both endpoints, such as gpt-5.2, are sent to Copilot's /chat/completions unless their model_info sets mode: responses

GitHub Copilot Responses

import litellm

response = await litellm.aresponses(
    model="github_copilot/gpt-5.3-codex",
    input="Write a Python hello world",
    max_output_tokens=500
)

print(response)

Anthropic Messages

Claude models can be called through Copilot's native Anthropic /v1/messages endpoint.

GitHub Copilot Anthropic Messages

import litellm

response = await litellm.anthropic.messages.acreate(
    model="github_copilot/claude-sonnet-4.5",
    messages=[{"role": "user", "content": "Write a Python hello world"}],
    max_tokens=500,
)

print(response)

Embedding

GitHub Copilot Embedding

import litellm

response = litellm.embedding(
    model="github_copilot/text-embedding-3-small",
    input=["good morning from litellm"]
)
print(response)

Usage - LiteLLM Proxy

Add the following to your LiteLLM Proxy configuration file:

config.yaml

model_list:
  - model_name: github_copilot/gpt-5.2
    litellm_params:
      model: github_copilot/gpt-5.2
  - model_name: github_copilot/gpt-5.3-codex
    model_info:
      mode: responses
    litellm_params:
      model: github_copilot/gpt-5.3-codex
  - model_name: github_copilot/claude-sonnet-4.5
    litellm_params:
      model: github_copilot/claude-sonnet-4.5
  - model_name: github_copilot/text-embedding-ada-002
    model_info:
      mode: embedding
    litellm_params:
      model: github_copilot/text-embedding-ada-002

Start your LiteLLM Proxy server:

Start LiteLLM Proxy

litellm --config config.yaml

# RUNNING on http://0.0.0.0:4000

OpenAI SDK

GitHub Copilot via Proxy - Non-streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-proxy-api-key"       # Your proxy API key
)

# Non-streaming response
response = client.chat.completions.create(
    model="github_copilot/gpt-5.2",
    messages=[{"role": "user", "content": "How do I optimize this SQL query?"}]
)

print(response.choices[0].message.content)

LiteLLM SDK

GitHub Copilot via Proxy - LiteLLM SDK

import litellm

# Configure LiteLLM to use your proxy
response = litellm.completion(
    model="litellm_proxy/github_copilot/gpt-5.2",
    messages=[{"role": "user", "content": "Review this code for bugs"}],
    api_base="http://localhost:4000",
    api_key="your-proxy-api-key"
)

print(response.choices[0].message.content)

cURL

GitHub Copilot via Proxy - cURL

curl http://localhost:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-proxy-api-key" \
  -d '{
    "model": "github_copilot/gpt-5.2",
    "messages": [{"role": "user", "content": "Explain this error message"}]
  }'

Responses and Anthropic Messages requests go to the proxy's /v1/responses and /v1/messages routes:

GitHub Copilot via Proxy - Responses and Messages

curl http://localhost:4000/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-proxy-api-key" \
  -d '{
    "model": "github_copilot/gpt-5.3-codex",
    "input": "Write a Python hello world"
  }'

curl http://localhost:4000/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-proxy-api-key" \
  -d '{
    "model": "github_copilot/claude-sonnet-4.5",
    "max_tokens": 500,
    "messages": [{"role": "user", "content": "Write a Python hello world"}]
  }'

Getting Started

1. Ensure you have GitHub Copilot access (paid GitHub subscription required)
2. Run your first LiteLLM request - you'll be prompted to authenticate
3. Follow the device flow authentication process
4. Start making requests to GitHub Copilot through LiteLLM

Configuration

Environment Variables

You can customize token storage locations:

Environment Variables

# Optional: Custom token directory
export GITHUB_COPILOT_TOKEN_DIR="~/.config/litellm/github_copilot"

# Optional: Custom access token file name
export GITHUB_COPILOT_ACCESS_TOKEN_FILE="access-token"

# Optional: Custom API key file name
export GITHUB_COPILOT_API_KEY_FILE="api-key.json"

# Optional: Custom Copilot endpoints for authentication and usage
# (needed when using GitHub Enterprise subscriptions with custom endpoints or self-hosted GitHub servers
export GITHUB_COPILOT_API_BASE="https://copilot-api.my-company.ghe.com"
export GITHUB_COPILOT_DEVICE_CODE_URL="https://my-company.ghe.com/login/device/code"
export GITHUB_COPILOT_ACCESS_TOKEN_URL="https://my-company.ghe.com/login/oauth/access_token"
export GITHUB_COPILOT_API_KEY_URL="https://my-company.ghe.com/api/v3/copilot_internal/v2/token"

# Optional: Custom OAuth client ID for the device flow
export GITHUB_COPILOT_CLIENT_ID="Iv1.b507a08c87ecfe98"

Headers

LiteLLM automatically injects the required GitHub Copilot headers (simulating VS Code Copilot Chat). You don't need to specify them manually.

If you want to override the defaults (e.g., to simulate a different editor), you can use extra_headers. These are the defaults LiteLLM sends on chat, responses, and embedding requests:

Custom Headers (Optional)

extra_headers = {
    "editor-version": "vscode/1.95.0",                 # Editor version
    "editor-plugin-version": "copilot-chat/0.26.7",    # Plugin version
    "copilot-integration-id": "vscode-chat",           # Integration ID
    "user-agent": "GitHubCopilotChat/0.26.7"           # User agent
}