Copilot API Proxy

Important Notes

Important

Before using, please be aware of the following:

Claude Code configuration: When using with Claude Code, please configure the model ID as claude-opus-4-6 or claude-opus-4.6 (without the [1m] suffix, exceeding GitHub Copilot's context window limit too much may lead to being banned). Example claude settings.json see Manual Configuration with settings.json.
Recommend for Opencode: For opencode, prefer the opencode OAuth app. It matches opencode's built-in GitHub Copilot provider and avoids Terms of Service risk:
```
npx @jeffreycao/copilot-api@latest --oauth-app=opencode start
```
Built-in codex provider: Run npx @jeffreycao/copilot-api@latest auth login --provider codex once and the gateway will persist and refresh Codex OAuth credentials automatically.
Disable multi agent when using codex: If you're using codex via GitHub Copilot, disable multi agent. Copilot currently charges codex traffic based on whether the last message is a user role, and that billing logic has not been adjusted.
Note: See GitHub Copilot Security Notice for the warning removed from the README header.

Project Overview

A reverse-engineered GitHub Copilot integration that also works as a small AI gateway. Besides Copilot, it can route the built-in codex provider and configured third-party providers such as DashScope behind OpenAI- and Anthropic-compatible APIs, so tools like Claude Code can use one local endpoint.

On the GitHub Copilot path, the gateway prefers Copilot's native Anthropic-style Messages API when available, preserving more Claude-native behavior for tool-heavy workflows.

Features

OpenAI and Anthropic compatibility: Serve /v1/responses, /v1/chat/completions, /v1/models, /v1/embeddings, and /v1/messages from one local gateway.
One gateway for Copilot, codex, and external providers: Route GitHub Copilot, the built-in codex provider, and configured third-party providers behind the same endpoint.
Agent-friendly Claude handling on Copilot: Prefer native /v1/messages when available, preserve Claude-style tool flows, support Anthropic beta features, and keep subagent/session markers intact.
Claude Code and OpenCode integration: Works with Claude Code and OpenCode, including direct Anthropic-compatible usage through @ai-sdk/anthropic.
Flexible auth and deployment options: Supports interactive login or direct tokens, individual/business/enterprise plans, GitHub Enterprise, opencode OAuth, and custom data directories.
Local control and visibility: Includes a usage dashboard, rate limiting, manual approval, and optional token visibility for debugging.
Multi-provider routing: Expose provider-specific /:provider/... routes or use model: "provider/model" on the top-level API.
Better token and context management: Supports exact Claude token counting and configurable GPT context compaction for long-running conversations.

Prerequisites

Bun (>= 1.2.x)
Node.js if you plan to run the published CLI with npx
GitHub account with Copilot subscription (individual, business, or enterprise)

Installation

To install dependencies, run:

bun install

To start the server directly from source:

bun run start start

Using with npx

You can run the project directly using npx:

Important

Token usage storage uses Node's built-in node:sqlite module when running with npx. It is enabled on Node.js >= 22.13.0. On Node.js < 22.13.0, the CLI still starts, but token usage storage is disabled.

If you want token usage storage without upgrading Node.js, run the published CLI with Bun instead: bunx --bun @jeffreycao/copilot-api@latest start.

npx @jeffreycao/copilot-api@latest start

With options:

npx @jeffreycao/copilot-api@latest start --port 8080

For authentication only:

npx @jeffreycao/copilot-api@latest auth

Electron Desktop App

If you prefer a GUI, this repository also includes an Electron desktop app in desktop/. It supports GitHub Copilot sign-in or manual token entry, can start and stop the local proxy with one click, and shows the local endpoint, auth header, available models, usage, and logs in the app.

The settings screen also exposes OAuth App, API Home, Enterprise URL, verbose logging, and minimize-to-tray. Desktop packages are published in GitHub Releases:

https://github.com/caozhiyuan/copilot-api/releases

Download the installer for your platform, sign in inside the app, choose a port, start the server, then point your client at the local endpoint shown in the app. Packaged desktop builds use the bundled Electron runtime, so normal desktop usage does not require installing Node.js separately. Token usage history is enabled when that bundled runtime supports SQLite.

The desktop app's Advanced Config page reads and writes model mappings through GET/POST /admin/config/model-mappings. It uses auth.adminApiKey instead of the regular auth.apiKeys, and the app reads that key directly from config.json after the server has generated it on startup.

Desktop App Screenshots

Main dashboard, token usage breakdown in the bundled Electron app:

Using with Docker

Build the image:

docker build -t copilot-api .

Run the container with a bind mount so auth data survives restarts:

mkdir -p ./copilot-data
docker run -p 4141:4141 -v $(pwd)/copilot-data:/root/.local/share/copilot-api copilot-api

This stores GitHub auth data in ./copilot-data on the host, mapped to /root/.local/share/copilot-api in the container.

Or pass a GitHub token directly:

docker run -p 4141:4141 -e GH_TOKEN=your_github_token_here copilot-api

Command Structure

Copilot API now uses a subcommand structure with these main commands:

start: Start the Copilot API server. This command will also handle authentication if needed.
auth: Run GitHub authentication flow without starting the server. This is typically used if you need to generate a token for use with the --github-token option, especially in non-interactive environments.
check-usage: Show your current GitHub Copilot usage and quota information directly in the terminal (no server required).
debug: Display diagnostic information including version, runtime details, file paths, and authentication status. Useful for troubleshooting and support.

Command Line Options

Global Options

The following options can be used with any subcommand. When passing them before the subcommand, use the --key=value form:

Option	Description	Default	Alias
--api-home	Path to the API home directory (sets COPILOT_API_HOME)	none	none
--oauth-app	OAuth app identifier (sets COPILOT_API_OAUTH_APP)	none	none
--enterprise-url	Enterprise URL for GitHub (sets COPILOT_API_ENTERPRISE_URL)	none	none

Start Command Options

The following command line options are available for the start command:

Option	Description	Default	Alias
--port	Port to listen on	4141	-p
--verbose	Enable verbose logging	false	-v
--account-type	Account type to use (individual, business, enterprise)	individual	-a
--manual	Enable manual request approval	false	none
--rate-limit	Rate limit in seconds between requests	none	-r
--wait	Wait instead of error when rate limit is hit	false	-w
--github-token	Provide GitHub token directly (must be generated using the `auth` subcommand)	none	-g
--claude-code	Generate a command to launch Claude Code with Copilot API config	false	-c
--show-token	Show GitHub and Copilot tokens on fetch and refresh	false	none
--proxy-env	Initialize proxy from environment variables	false	none

Auth Command Options

Option	Description	Default	Alias
--verbose	Enable verbose logging	false	-v
--show-token	Show GitHub token on auth	false	none

Debug Command Options

Option	Description	Default	Alias
--json	Output debug info as JSON	false	none

Configuration (config.json)

Location: ~/.local/share/copilot-api/config.json (Linux/macOS) or %USERPROFILE%\.local\share\copilot-api\config.json (Windows).

Default shape:

{
  "auth": {
    "apiKeys": [],
    "adminApiKey": "<auto-generated-on-startup>"
  },
  "providers": {
    "custom": {
      "type": "anthropic",
      "enabled": true,
      "baseUrl": "your-base-url",
      "apiKey": "sk-your-provider-key",
      "authType": "x-api-key",
      "adjustInputTokens": false,
      "models": {
        "kimi-k2.5": {
          "temperature": 1,
          "topP": 0.95
        }
      }
    },
    "dashscope": {
      "type": "openai-compatible",
      "enabled": true,
      "baseUrl": "https://dashscope.aliyuncs.com/compatible-mode",
      "apiKey": "sk-your-dashscope-key",
      "models": {
        "qwen3.6-plus": {
          "temperature": 1,
          "topP": 0.95,
          "topK": 20,
          "extraBody": {
            "preserve_thinking": true
          },
          "contextCache": true
        },
        "glm-5.1": {
          "temperature": 0.7,
          "topP": 0.95,
          "contextCache": true,
          "extraBody": {
            "preserve_thinking": true
          }
        }
      }
    }
  },
  "modelMappings": {},
  "extraPrompts": {
    "gpt-5-mini": "<built-in exploration prompt>",
    "gpt-5.3-codex": "<built-in commentary prompt>",
    "gpt-5.4-mini": "<built-in commentary prompt>",
    "gpt-5.4": "<built-in commentary prompt>"
  },
  "smallModel": "gpt-5-mini",
  "responsesApiContextManagementModels": [],
  "modelReasoningEfforts": {
    "gpt-5-mini": "low",
    "gpt-5.3-codex": "xhigh",
    "gpt-5.4-mini": "xhigh",
    "gpt-5.4": "xhigh"
  },
  "useMessagesApi": true,
  "useResponsesApiWebSocket": true,
  "useResponsesApiWebSearch": true
}

auth.apiKeys: API keys used for request authentication on non-admin routes. Supports multiple keys for rotation. Requests can authenticate with either x-api-key: <key> or Authorization: Bearer <key>. If empty or omitted, authentication for non-admin routes is disabled.
auth.adminApiKey: Single admin key used only for /admin/* routes. If missing, the server generates a random key at startup and writes it back to config.json. Requests use the same x-api-key or Authorization: Bearer headers, but regular auth.apiKeys never grant access to /admin/*.
modelMappings: Exact sourceModel -> targetModel rewrites for top-level POST /v1/messages and POST /v1/messages/count_tokens requests. Omit it or leave it as {} to disable rewrites. Both the source and target must be non-empty strings. Targets can be regular model IDs or provider/model aliases such as dashscope/qwen3.6-plus, and the rewrite happens before provider alias parsing. The admin endpoints GET/POST /admin/config/model-mappings read and update only this field.
extraPrompts: Map of model -> prompt appended to the first system prompt when translating Anthropic-style requests to Copilot. Use this to inject guardrails or guidance per model. Missing default entries are auto-added without overwriting your custom prompts. The built-in prompts for gpt-5.3-codex and gpt-5.4 enable phase-aware commentary, which lets the model emit a short user-facing progress update before tools or deeper reasoning.
providers: Global upstream provider map. Each provider key (for example dashscope) becomes a route prefix (/dashscope/v1/messages). Supports type: "anthropic", type: "openai-compatible", and type: "openai-responses". Top-level clients can also use model: "dashscope/model-id" with /v1/messages, /v1/messages/count_tokens, and /v1/responses; the gateway strips the dashscope/ prefix before forwarding upstream. GET /v1/models does not aggregate provider models; use GET /dashscope/v1/models for provider model lists.
- enabled defaults to true if omitted.
- baseUrl should be provider API base URL without the final endpoint. For Anthropic providers, omit /v1/messages; for OpenAI-compatible providers, omit /v1/chat/completions; for OpenAI Responses providers, omit /v1/responses.
- apiKey is used as the upstream credential value and is required for regular providers.
- authType (optional): Controls how apiKey is sent upstream. Supports x-api-key and authorization for regular providers. Anthropic providers default to x-api-key; OpenAI-compatible and OpenAI Responses providers default to authorization. When set to authorization, the proxy sends Authorization: Bearer <apiKey>. oauth2 is reserved for the built-in codex provider and is written automatically by auth login --provider codex.
- adjustInputTokens (optional): When true, the proxy will adjust the input_tokens in the usage response by subtracting cache_read_input_tokens and cache_creation_input_tokens.
- models (optional): Per-model configuration map. Each key is a model ID (matching the model name in requests), and the value is:
  - temperature (optional): Default temperature value used when the request does not specify one.
  - topP (optional): Default top_p value used when the request does not specify one.
  - topK (optional): Default top_k value used when the request does not specify one.
  - extraBody (optional): Dynamic fields merged into the upstream request body for that model. Request body fields with the same name take precedence. OpenAI-compatible providers can use this for fields such as enable_thinking, preserve_thinking, reasoning_effort. thinking_budget is a special OpenAI-compatible provider override: when configured in extraBody, it is forced after Anthropic thinking.budget_tokens translation and overrides the request-derived budget.
  - contextCache (optional): Defaults to true for OpenAI-compatible providers. This enables Alibaba Cloud Model Studio/DashScope explicit context cache by injecting cache_control: { "type": "ephemeral" } on up to 4 content blocks using the Context Cache format. The cache breakpoint strategy matches opencode's main provider flow: the first 2 system messages plus the last 2 non-system messages. Marked string content is converted to text content part arrays for system / user / assistant / tool messages; existing array content is marked on the last part. Set this to false when the model already supports implicit caching, or when the upstream does not accept this explicit-cache extension field.
  - supportPdf (optional): Controls whether the model supports PDF/document content. Defaults to false; unsupported PDFs are converted to a text notice. Set it to true to send PDF/document blocks as OpenAI Chat Completions file parts.
  - toolContentSupportType (optional): Tool result content capabilities for that model, as an array of array, image, and pdf. Provider routes default to string-only tool content when omitted. If supportPdf is true but this list does not include pdf, file parts in tool results are moved to user role messages. This provider default does not change the Copilot main flow, which continues to support array + image and not PDF.
smallModel: Fallback model used for tool-less warmup messages (e.g., Claude Code probe requests); defaults to gpt-5-mini.
responsesApiContextManagementModels: List of GPT model IDs that should receive Responses API context_management compaction instructions. This defaults to [], so you need to opt in explicitly. A good starting point is ["gpt-5-mini", "gpt-5.3-codex", "gpt-5.4-mini", "gpt-5.4"]. When enabled, the request includes context_management in the body and keeps only the latest compaction carrier on follow-up turns. The actual compaction is handled server-side and appears to begin when usage approaches roughly 90% of the model's maxPromptTokens, which makes it especially useful for long-running tasks. In practice, the effective compact_threshold also appears to be fixed on the server side, so changing it in this project does not currently alter compaction behavior. At the moment, this optimization is intended for GPT-family models only.
modelReasoningEfforts: Per-model reasoning.effort sent to the Copilot Responses API. Allowed values are none, minimal, low, medium, high, and xhigh. If a model isn’t listed, high is used by default.
useMessagesApi: When true, Claude-family models that support Copilot's native /v1/messages endpoint will use the Messages API; otherwise they fall back to /chat/completions. Set to false to disable Messages API routing and always use /chat/completions. Defaults to true.
useResponsesApiWebSocket: When true, Responses API requests use Copilot's websocket transport for models that advertise ws:/responses; models that only advertise /responses continue to use HTTP. Set to false to disable websocket routing and use HTTP /responses whenever the selected model supports it. Defaults to true.
useResponsesApiWebSearch: When true, the server keeps Responses API tools with type: "web_search" and forwards them upstream. Set to false to strip those tools from /responses payloads. Defaults to true.
claudeTokenMultiplier: Multiplier applied to the fallback GPT-tokenizer estimate for Claude /v1/messages/count_tokens requests. Defaults to 1.15. Increase it if your client is still compacting too late. This setting is only used when the proxy is estimating Claude tokens locally; if anthropicApiKey is configured and Anthropic token counting succeeds, the exact Anthropic count is returned instead.
anthropicApiKey: Anthropic API key used to forward Claude /v1/messages/count_tokens requests to Anthropic's real token counting endpoint, which returns exact counts instead of GPT tokenizer estimates. Can also be set via the ANTHROPIC_API_KEY environment variable. If not set, or if the upstream call fails, token counting falls back to local GPT tokenizer estimation controlled by claudeTokenMultiplier.

Edit this file to customize prompts or swap in your own fast model. Restart the server (or rerun the command) after changes so the cached config is refreshed.

API Authentication

Protected non-admin routes: All routes except /, /usage-viewer, and /usage-viewer/ require authentication when auth.apiKeys is configured and non-empty.
Admin routes: All /admin/* routes require auth.adminApiKey. If it is missing, the server generates one at startup and persists it to config.json before serving requests.
Allowed auth headers:
- x-api-key: <your_key>
- Authorization: Bearer <your_key>
CORS preflight: OPTIONS requests are always allowed.
When no regular keys are configured: Non-admin routes continue to allow requests. This does not apply to /admin/*, which only accepts auth.adminApiKey.

Example request for a regular protected route:

curl http://localhost:4141/v1/models \
  -H "x-api-key: your_api_key"

Example request for an admin route:

curl http://localhost:4141/admin/config/model-mappings \
  -H "x-api-key: your_admin_api_key"

API Endpoints

The server exposes several endpoints to interact with the Copilot API. It provides OpenAI-compatible endpoints and now also includes support for Anthropic-compatible endpoints, allowing for greater flexibility with different tools and services.

OpenAI Compatible Endpoints

These endpoints mimic the OpenAI API structure.

Endpoint	Method	Description
`POST /v1/responses`	`POST`	OpenAI Most advanced interface for generating model responses. Supports `provider/model` aliases for `openai-responses` providers.
`POST /v1/chat/completions`	`POST`	Creates a model response for the given chat conversation.
`GET /v1/models`	`GET`	Lists the currently available models.
`POST /v1/embeddings`	`POST`	Creates an embedding vector representing the input text.

Anthropic Compatible Endpoints

These endpoints are designed to be compatible with the Anthropic Messages API.

Endpoint	Method	Description
`POST /v1/messages`	`POST`	Creates a model response for a given conversation. Supports `provider/model` aliases for configured providers.
`POST /v1/messages/count_tokens`	`POST`	Calculates the number of tokens for a given set of messages. Supports `provider/model` aliases for configured providers.
`POST /:provider/v1/messages`	`POST`	Proxies Anthropic Messages requests to the configured Anthropic, OpenAI-compatible, or OpenAI Responses provider.
`GET /:provider/v1/models`	`GET`	Proxies model listing requests to the configured provider.
`POST /:provider/v1/messages/count_tokens`	`POST`	Calculates tokens locally for provider route requests.

Usage Monitoring Endpoints

New endpoints for monitoring your Copilot usage and quotas.

Endpoint	Method	Description
`GET /usage`	`GET`	Get detailed Copilot usage statistics and quota information.
`GET /token`	`GET`	Get the current Copilot token being used by the API.

Admin / Configuration Endpoints

These endpoints are reserved for local administrative actions and only accept auth.adminApiKey.

Endpoint	Method	Description
`GET /admin/config/model-mappings`	`GET`	Returns the current `config.json` path and the active `modelMappings` map.
`POST /admin/config/model-mappings`	`POST`	Updates only the `modelMappings` field in `config.json` and returns it back.

Example Usage

Common npx commands:

# Start the gateway
npx @jeffreycao/copilot-api@latest start

# Start on a custom port with verbose logging
npx @jeffreycao/copilot-api@latest start --port 8080 --verbose

# Run the auth flow
npx @jeffreycao/copilot-api@latest auth login

# Check Copilot usage without starting the server
npx @jeffreycao/copilot-api@latest check-usage

# Print debug information as JSON
npx @jeffreycao/copilot-api@latest debug --json

# Run the published CLI with Bun instead of Node.js
bunx --bun @jeffreycao/copilot-api@latest start

Using with Claude Code

This AI gateway can be used to power Claude Code, an experimental conversational AI assistant for developers from Anthropic.

There are two ways to configure Claude Code to use this AI gateway:

Interactive Setup with `--claude-code` flag

To get started, run the start command with the --claude-code flag:

npx @jeffreycao/copilot-api@latest start --claude-code

You will be prompted to select a primary model and a "small, fast" model for background tasks. After selecting the models, a command will be copied to your clipboard. This command sets the necessary environment variables for Claude Code to use the gateway.

Paste and run this command in a new terminal to launch Claude Code.

Manual Configuration with `settings.json`

Alternatively, you can configure Claude Code by creating a .claude/settings.json file in your project's root directory. This file should contain the environment variables needed by Claude Code. This way you don't need to run the interactive setup every time.

Here is an example .claude/settings.json file:

{
  "env": {
    "ANTHROPIC_BASE_URL": "http://localhost:4141",
    "ANTHROPIC_AUTH_TOKEN": "dummy",
    "ANTHROPIC_MODEL": "gpt-5.4",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "gpt-5.4",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "gpt-5-mini",
    "DISABLE_NON_ESSENTIAL_MODEL_CALLS": "1",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1",
    "CLAUDE_CODE_ATTRIBUTION_HEADER": "0",
    "CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION": "false",
    "CLAUDE_CODE_DISABLE_TERMINAL_TITLE": "true",
    "CLAUDE_CODE_ENABLE_AWAY_SUMMARY": "0",
    "CLAUDE_PLUGIN_ENABLE_QUESTION_RULES": "true"
  },
  "permissions": {
    "deny": [
      "WebSearch", 
      "mcp__ide__executeCode"
    ]
  }
}

Replace ANTHROPIC_MODEL, ANTHROPIC_DEFAULT_OPUS_MODEL, ANTHROPIC_DEFAULT_SONNET_MODEL, and ANTHROPIC_DEFAULT_HAIKU_MODEL according to your needs. After configuration, please install the claude code plugin Plugin Integrations. If configuring the claude model, it is recommended to set all model configurations the same, so as to remain consistent with github-copilot claude agent behavior.
Setting CLAUDE_CODE_ATTRIBUTION_HEADER to 0 can prevent Claude code from adding billing and version information in system prompts, thereby avoiding prompt cache invalidation.
Turning off CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION and CLAUDE_CODE_ENABLE_AWAY_SUMMARY can prevent quota from being consumed unnecessarily.
Permissions deny WebSearch because the GitHub Copilot API does not support natie websearch (some gpt models support websearch, but the current project has not adapted websearch); it is recommended to install the mcp mcp_server_fetch tool or other search tools as alternatives..
If using a non-Claude model, do not enable ENABLE_TOOL_SEARCH. If using the Claude model, can enable ENABLE_TOOL_SEARCH. The current Claude Code uses the client tool search mode. In this mode, loading defer tools requires an additional request each time.

You can find more options here: Claude Code settings

You can also read more about IDE integration here: Add Claude Code to your IDE

GPT Tool Search

For GPT Responses models such as gpt-5.4+, this AI gateway can expose Responses tool_search through a small MCP bridge. The same bridge can be used by Claude Code and opencode, as long as the client loads MCP servers and sends Anthropic Messages traffic through this gateway.

Do not set Claude Code's native ENABLE_TOOL_SEARCH for GPT models. That flag enables Claude Code's own client-side tool search mode, and it may stop forwarding deferred tool definitions. This gateway needs the full tool definitions so it can keep the small always-loaded tool set eager and translate every other tool into Responses deferred namespaces.

If you install tool-search@copilot-api-marketplace, Claude Code receives this MCP bridge automatically and you can skip the manual Claude Code MCP setup below.

Add the tool search bridge to the MCP config used by Claude Code:

{
  "mcpServers": {
    "tool_search": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@jeffreycao/copilot-api@latest", "mcp"]
    }
  }
}

Add the tool search bridge to the MCP config used by opencode:

{
  "mcp": {
    "tool_search": {
      "type": "local",
      "command": ["npx", "-y", "@jeffreycao/copilot-api@latest", "mcp"]
    }
  }
}

For local development, use bun as the command and ["run", "./src/main.ts", "mcp"] as the args.

Internally, the gateway now configures OpenAI Responses tool_search in client-executed mode. Deferred tools are still exposed as searchable namespaces, but the model is explicitly asked to return the exact deferred tool names it wants to load next.

The bridge uses direct tool selection, not query search. Its tool input is names, a comma-separated list of exact deferred tool names, for example TaskList,TaskGet,mcp__fetch__fetch.

Using with OpenCode

OpenCode already has a direct GitHub Copilot provider. Use this section when you want OpenCode to point at this AI gateway through @ai-sdk/anthropic and reuse the agent behaviors described earlier in this README.

Minimal setup

Start the AI gateway with the OpenCode OAuth app:

npx @jeffreycao/copilot-api@latest --oauth-app=opencode start

Then point OpenCode at the gateway with @ai-sdk/anthropic.

Example ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "model": "local/gpt-5.4",
  "small_model": "local/gpt-5-mini",
  "agent": {
    "build": {
      "model": "local/gpt-5.4"
    },
    "plan": {
      "model": "local/gpt-5.4"
    },
    "explore": {
      "model": "local/gpt-5-mini"
    }
  },
  "provider": {
    "local": {
      "npm": "@ai-sdk/anthropic",
      "name": "Copilot API Proxy",
      "options": {
        "baseURL": "http://localhost:4141/v1",
        "apiKey": "dummy"
      },
      "models": {
        "gpt-5.4": {
          "name": "gpt-5.4",
          "modalities": {
            "input": ["text", "image"],
            "output": ["text"]
          },
          "limit": {
            "context": 272000,
            "output": 128000
          }
        },
        "gpt-5-mini": {
          "name": "gpt-5-mini",
          "limit": {
            "context": 128000,
            "output": 64000
          }
        },
        "claude-sonnet-4.6": {
          "id": "claude-sonnet-4.6",
          "name": "claude-sonnet-4.6",
          "modalities": {
            "input": ["text", "image"],
            "output": ["text"]
          },          
          "limit": {
            "context": 128000,
            "output": 32000
          },
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 31999
            }
          }
        }
      }
    }
  }
}

Why these fields matter:

npm: "@ai-sdk/anthropic" is the important part. OpenCode will speak Anthropic Messages semantics to this AI gateway instead of flattening everything into OpenAI Chat Completions.
options.baseURL should be http://localhost:4141/v1; the Anthropic SDK will append /messages, /models, and /messages/count_tokens automatically.
model, small_model, and agent.*.model let you keep gpt-5.4 for build/plan work while routing exploration and background work to gpt-5-mini.
If you enable auth.apiKeys in this AI gateway, replace dummy with a real key. Otherwise any placeholder value is fine.

Plugin Integrations

Plugin integrations are available for Claude Code and opencode.

Claude Code plugin integration (marketplace-based)

The Claude Code integration is packaged as two plugins:

agent-inject injects __SUBAGENT_MARKER__... on SubagentStart, so the gateway can infer x-initiator: agent.
tool-search registers the tool_search MCP bridge used for GPT Responses deferred tool loading.
Marketplace catalog in this repository: .claude-plugin/marketplace.json
Plugin sources in this repository: plugin/claude/agent-inject, plugin/claude/tool-search

Add the marketplace remotely:

/plugin marketplace add https://github.com/caozhiyuan/copilot-api.git

Install the plugins from the marketplace:

/plugin install agent-inject@copilot-api-marketplace
/plugin install tool-search@copilot-api-marketplace

After installation, agent-inject injects __SUBAGENT_MARKER__... on SubagentStart, and the gateway uses it to infer x-initiator: agent.

The agent-inject plugin also registers a UserPromptSubmit hook that returns {"continue": true}, and it can inject SessionStart reminder rules through environment variables:

CLAUDE_PLUGIN_ENABLE_QUESTION_RULES=1 enables the two reminders about using the question tool automatically for Claude Code. Alternatively, you can add the same reminders manually in CLAUDE.md; see CLAUDE.md or AGENTS.md Recommended Content.
CLAUDE_PLUGIN_ENABLE_NO_BACKGROUND_AGENTS_RULE=1 enables the run_in_background: true avoidance reminder for agent hooks.

The tool-search plugin bundles the same MCP bridge described in GPT Tool Search, so Claude Code users do not need to add the tool_search server manually when they install that plugin.

Opencode plugin

The subagent marker producer is packaged as an opencode plugin located at plugin/opencode/subagent-marker.js.

Installation:

Copy the plugin file to your opencode plugins directory:

# Clone or download this repository, then copy the plugin
cp plugin/opencode/subagent-marker.js ~/.config/opencode/plugins/

Or manually create the file at ~/.config/opencode/plugins/subagent-marker.js with the plugin content.

Features:

Tracks sub-sessions created by subagents
Automatically prepends a marker system reminder (__SUBAGENT_MARKER__...) to subagent chat messages
Sets x-session-id header for session tracking
Enables the gateway to infer x-initiator: agent for subagent-originated requests

The plugin hooks into session.created, session.deleted, chat.message, and chat.headers events to provide seamless subagent marker functionality.

Using the Usage Viewer

After starting the server, a URL to the Copilot Usage Dashboard will be displayed in your console. This dashboard is a web interface for monitoring your API usage.

Start the server. For example, using npx:
```
npx @jeffreycao/copilot-api@latest start
```
The server will output a URL to the usage viewer. Copy and paste this URL into your browser. It will look something like this: http://localhost:4141/usage-viewer?endpoint=http://localhost:4141/usage
- If you use the start.bat script on Windows, this page will open automatically.

The dashboard provides a user-friendly interface to view your Copilot usage data:

Token usage history requires Bun or Node.js >= 22.13.0. On Node.js < 22.13.0, the server runs normally but token usage storage is disabled.

API Endpoint URL: The dashboard is pre-configured to fetch data from your local server endpoint via the URL query parameter. You can change this URL to point to any other compatible API endpoint.
Fetch Data: Click the "Fetch" button to load or refresh the usage data. The dashboard will automatically fetch data on load.
Usage Quotas: View a summary of your usage quotas for different services like Chat and Completions, displayed with progress bars for a quick overview.
Detailed Information: See the full JSON response from the API for a detailed breakdown of all available usage statistics.
URL-based Configuration: You can also specify the API endpoint directly in the URL using a query parameter. This is useful for bookmarks or sharing links. For example: http://localhost:4141/usage-viewer?endpoint=http://your-api-server/usage

Usage Viewer Screenshot

Running from Source

The project can be run from source in several ways:

Development Mode

bun run dev start

Production Mode

bun run start start

Usage Tips

To avoid hitting GitHub Copilot's rate limits, you can use the following flags:
- --manual: Enables manual approval for each request, giving you full control over when requests are sent.
- --rate-limit <seconds>: Enforces a minimum time interval between requests. For example, copilot-api start --rate-limit 30 will ensure there's at least a 30-second gap between requests.
- --wait: Use this with --rate-limit. It makes the server wait for the cooldown period to end instead of rejecting the request with an error. This is useful for clients that don't automatically retry on rate limit errors.
If you have a GitHub business or enterprise plan account with Copilot, use the --account-type flag (e.g., --account-type business). See the official documentation for more details.

CLAUDE.md or AGENTS.md Recommended Content

To add these reminders manually, include the following in CLAUDE.md for Claude Code, or AGENTS.md for opencode/codex:

- Prohibited from directly asking questions to users, MUST use question tool.
- Once you can confirm that the task is complete, MUST use question tool to make user confirm. The user may respond with feedback if they are not satisfied with the result, which you can use to make improvements and try again, after try again, MUST use question tool to make user confirm again.

Name		Name	Last commit message	Last commit date
Latest commit History 818 Commits
.claude-plugin		.claude-plugin
.github		.github
.vscode		.vscode
desktop		desktop
docs/screenshots		docs/screenshots
pages		pages
plugin		plugin
src		src
tests		tests
.dockerignore		.dockerignore
.gitignore		.gitignore
AGENTS.md		AGENTS.md
CLAUDE.md		CLAUDE.md
Dockerfile		Dockerfile
LICENSE		LICENSE
NOTICE.md		NOTICE.md
README.md		README.md
README.zh-CN.md		README.zh-CN.md
bun.lock		bun.lock
entrypoint.sh		entrypoint.sh
eslint.config.js		eslint.config.js
package-lock.json		package-lock.json
package.json		package.json
start.bat		start.bat
tsconfig.json		tsconfig.json
tsdown.config.ts		tsdown.config.ts
tsdown.desktop.config.ts		tsdown.desktop.config.ts

Folders and files

Latest commit

History

Repository files navigation

Copilot API Proxy

Important Notes

Project Overview

Features

Prerequisites

Installation

Using with npx

Electron Desktop App

Desktop App Screenshots

Using with Docker

Command Structure

Command Line Options

Global Options

Start Command Options

Auth Command Options

Debug Command Options

Configuration (config.json)

API Authentication

API Endpoints

OpenAI Compatible Endpoints

Anthropic Compatible Endpoints

Usage Monitoring Endpoints

Admin / Configuration Endpoints

Example Usage

Using with Claude Code

Interactive Setup with --claude-code flag

Manual Configuration with settings.json

GPT Tool Search

Using with OpenCode

Minimal setup

Plugin Integrations

Claude Code plugin integration (marketplace-based)

Opencode plugin

Using the Usage Viewer

Usage Viewer Screenshot

Running from Source

Development Mode

Production Mode

Usage Tips

CLAUDE.md or AGENTS.md Recommended Content

About

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Contributors

Uh oh!

Languages

Interactive Setup with `--claude-code` flag

Manual Configuration with `settings.json`

Packages