Welcome!
Enter an API endpoint URL and click "Fetch" to see usage data.
`;
}
```
--------------------------------
### Get Current Copilot Token
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Returns the active Copilot bearer token used for upstream requests. This is useful for debugging or direct access to the Copilot API.
```sh
curl -s http://localhost:4141/token | jq .
# Expected:
# { "token": "tid=...;exp=...;..." }
```
--------------------------------
### List Available Models with Copilot API
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Retrieve a list of all available models accessible through the Copilot API. The response is formatted similarly to the OpenAI API.
```bash
curl -s http://localhost:4141/v1/models \
-H "Authorization: Bearer dummy" | jq .
```
--------------------------------
### Build Docker Image with GitHub Token
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Build a Docker image for the Copilot API proxy, embedding a GitHub token during the build process. Replace 'your_github_token_here' with your actual token.
```sh
docker build --build-arg GH_TOKEN=your_github_token_here -t copilot-api .
```
--------------------------------
### Lint Project with ESLint
Source: https://github.com/ericc-ch/copilot-api/blob/master/AGENTS.md
Applies linting rules defined in @echristian/eslint-config to check code quality and style. Run this to auto-fix many style issues.
```bash
bun run lint
```
--------------------------------
### Run Docker Container with Options
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Run the Copilot API proxy in a Docker container with additional command-line options, such as enabling verbose output and specifying the port.
```sh
docker run -p 4141:4141 -e GH_TOKEN=your_token copilot-api start --verbose --port 4141
```
--------------------------------
### List available models
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Returns the list of Copilot models available to the authenticated account, in OpenAI list format.
```APIDOC
## GET /v1/models — List available models
### Description
Returns the list of Copilot models available to the authenticated account, in OpenAI list format.
### Method
GET
### Endpoint
/v1/models
### Request Example
```sh
curl -s http://localhost:4141/v1/models \
-H "Authorization: Bearer dummy" | jq .
```
### Response
#### Success Response (200)
- **object** (string) - Type of the response object.
- **data** (array) - List of available models.
- **id** (string) - Model identifier.
- **object** (string) - Type of the model object.
- **type** (string) - Type of the model.
- **created** (integer) - Model creation timestamp.
- **owned_by** (string) - The organization that owns the model.
- **display_name** (string) - User-friendly name for the model.
- **has_more** (boolean) - Indicates if there are more models to list.
```
--------------------------------
### POST /v1/chat/completions
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Accepts an OpenAI Chat Completions payload and proxies it to GitHub Copilot. Supports streaming via SSE, tool/function calling, and image inputs.
```APIDOC
## POST /v1/chat/completions
### Description
Accepts an OpenAI Chat Completions payload and proxies it to GitHub Copilot. Supports streaming via SSE, tool/function calling, image inputs, and automatically sets `max_tokens` from the model's capabilities if omitted.
### Method
POST
### Endpoint
/v1/chat/completions
### Request Body
- **model** (string) - Required - The model to use for generation.
- **messages** (array) - Required - An array of message objects representing the conversation history.
- **role** (string) - Required - The role of the message sender (e.g., "system", "user", "assistant").
- **content** (string) - Required - The content of the message.
- **stream** (boolean) - Optional - Whether to stream the response.
- **tools** (array) - Optional - A list of tools the model may call.
- **tool_choice** (object) - Optional - Controls how the tools are called.
### Request Example
```sh
# Non-streaming request
curl -s http://localhost:4141/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer dummy" \
-d '{ \
"model": "gpt-4o", \
"messages": [ \
{"role": "system", "content": "You are a helpful assistant."}, \
{"role": "user", "content": "What is 2+2?"} \
] \
}' | jq .
```
### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the completion.
- **object** (string) - Type of object returned (e.g., "chat.completion").
- **created** (integer) - Unix timestamp of creation.
- **model** (string) - The model used for the completion.
- **choices** (array) - A list of completion choices.
- **index** (integer) - Index of the choice.
- **message** (object) - The message content.
- **role** (string) - The role of the message sender.
- **content** (string) - The content of the message.
- **finish_reason** (string) - The reason the model stopped generating tokens.
#### Response Example
```json
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1714000000,
"model": "gpt-4o",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "2+2 equals 4."
},
"finish_reason": "stop"
}]
}
```
```
--------------------------------
### Build Docker Image
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Build the Docker image for the Copilot API proxy. This command creates a Docker image tagged as 'copilot-api'.
```sh
docker build -t copilot-api .
```
--------------------------------
### Run All Tests with Bun
Source: https://github.com/ericc-ch/copilot-api/blob/master/AGENTS.md
Executes all test files within the project using Bun's built-in test runner. Ensure tests are located in the 'tests/' directory and named with '*.test.ts'.
```bash
bun test
```
--------------------------------
### Test Single File with Bun
Source: https://github.com/ericc-ch/copilot-api/blob/master/AGENTS.md
Runs tests for a specific file. Useful for focused testing during development. Provide the relative path to the test file.
```bash
bun test tests/claude-request.test.ts
```
--------------------------------
### Run Docker Container with GitHub Token
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Run the Copilot API proxy in a Docker container, providing the GitHub token via an environment variable. This is an alternative to volume mounting for authentication.
```sh
docker run -p 4141:4141 -e GH_TOKEN=your_github_token_here copilot-api
```
--------------------------------
### Display Debug Information
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Show debug information for troubleshooting purposes.
```bash
npx copilot-api@latest debug
```
--------------------------------
### Run Copilot API with npx and Custom Port
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Run the Copilot API proxy using npx, specifying a custom port for the service. This allows you to avoid port conflicts.
```sh
npx copilot-api@latest start --port 8080
```
--------------------------------
### Streaming Chat Completions with Copilot API
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Make a streaming request to the chat completions endpoint. The response will be in Server-Sent Events (SSE) format.
```bash
curl -s http://localhost:4141/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer dummy" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Count to 3"}],
"stream": true
}'
```
--------------------------------
### Create Embeddings with Copilot API
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Generate embeddings for input text. This endpoint proxies requests to GitHub Copilot's embeddings service and returns results in OpenAI format.
```bash
curl -s http://localhost:4141/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer dummy" \
-d '{
"model": "text-embedding-3-small",
"input": ["Hello world", "Another sentence"]
}' | jq '{model: .model, count: (.data | length), dims: (.data[0].embedding | length)}'
```
--------------------------------
### Wait on Rate Limit Hit
Source: https://github.com/ericc-ch/copilot-api/blob/master/README.md
Instead of returning an error when the rate limit is hit, configure the server to wait using the --wait flag in conjunction with --rate-limit.
```bash
npx copilot-api@latest start --rate-limit 30 --wait
```
--------------------------------
### Tool Use with Anthropic Messages API
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Configure tool use for the Anthropic-compatible messages endpoint by providing tool definitions and specifying 'tool_choice'.
```bash
curl -s http://localhost:4141/v1/messages \
-H "Content-Type: application/json" \
-H "x-api-key: dummy" \
-d '{
"model": "claude-sonnet-4",
"max_tokens": 512,
"messages": [{"role": "user", "content": "Search for news about AI"}],
"tools": [{
"name": "web_search",
"description": "Search the web",
"input_schema": {
"type": "object",
"properties": { "query": { "type": "string" } },
"required": ["query"]
}
}],
"tool_choice": {"type": "auto"}
}' | jq .content
```
--------------------------------
### Create embeddings
Source: https://context7.com/ericc-ch/copilot-api/llms.txt
Proxies an embedding request directly to GitHub Copilot's embeddings endpoint and returns the result in OpenAI format.
```APIDOC
## POST /v1/embeddings — Create embeddings
### Description
Proxies an embedding request directly to GitHub Copilot's embeddings endpoint and returns the result in OpenAI format.
### Method
POST
### Endpoint
/v1/embeddings
### Parameters
#### Request Body
- **model** (string) - Required - The ID of the model to use for embedding.
- **input** (array of strings) - Required - The input texts to embed.
### Request Example
```sh
curl -s http://localhost:4141/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer dummy" \
-d
{
"model": "text-embedding-3-small",
"input": ["Hello world", "Another sentence"]
}
| jq
'{model: .model, count: (.data | length), dims: (.data[0].embedding | length)}'
```
### Response
#### Success Response (200)
- **model** (string) - The ID of the model used for embedding.
- **data** (array) - A list of embedding objects.
- **object** (string) - Type of the object.
- **embedding** (array of floats) - The embedding vector.
- **index** (integer) - The index of the input text.
- **usage** (object) - Usage statistics for the request.
- **prompt_tokens** (integer) - The number of tokens in the prompt.
- **total_tokens** (integer) - The total number of tokens processed.
```
--------------------------------
### Render Loading Spinner
Source: https://github.com/ericc-ch/copilot-api/blob/master/pages/index.html
Generates HTML for a centered loading spinner. Uses Tailwind CSS classes for animation and styling.
```javascript
function renderSpinner() {
return `