claude2api

Use a docker-compose.yml file to manage the deployment. This is useful for managing multiple environment variables and ensuring the service restarts automatically.

version: '3'
services:
  claude2api:
    image: ghcr.io/yushangxiao/claude2api:latest
    container_name: claude2api
    ports:
      - "8080:8080"
    environment:
      - SESSIONS=sk-ant-sid01-xxxx,sk-ant-sid01-yyyy
      - ADDRESS=0.0.0.0:8080
      - APIKEY=123
      - PROXY=http://proxy:2080  # Optional
      - CHAT_DELETE=true
      - MAX_CHAT_HISTORY_LENGTH=10000
      - NO_ROLE_PREFIX=false
      - PROMPT_DISABLE_ARTIFACTS=true
      - ENABLE_MIRROR_API=false
      - MIRROR_API_PREFIX=/mirror
    restart: unless-stopped

Then run:

docker-compose up -d

To deploy directly on your host machine, you need Go 1.23+ installed.

1. Clone the repository.
2. Copy the .env.example to .env and configure it.
3. Build the binary using go build.
4. Execute the binary.

# Clone the repository
git clone https://github.com/yushangxiao/claude2api.git
cd claude2api
cp .env.example .env  
# Edit .env with your configuration
# Build the binary
go build -o claude2api .

./claude2api

1. Fork the Hugging Face Space at https://huggingface.co/spaces/rclon/claude2api.
2. Configure your environment variables in the Settings tab.
3. The Space will automatically deploy the Docker image.

Note: In Hugging Face, the /v1 endpoint might be blocked; use /hf/v1 instead.

You can run Claude2Api as a containerized service using Docker. Ensure you provide the required SESSIONS (Claude session keys) and APIKEY (your custom authentication key) environment variables.

docker run -d \
  -p 8080:8080 \
  -e SESSIONS=sk-ant-sid01-xxxx,sk-ant-sid01-yyyy \
  -e APIKEY=123 \
  -e CHAT_DELETE=true \
  -e MAX_CHAT_HISTORY_LENGTH=10000 \
  -e NO_ROLE_PREFIX=false \
  -e PROMPT_DISABLE_ARTIFACTS=false \
  -e ENABLE_MIRROR_API=false \
  -e MIRROR_API_PREFIX=/mirror \
  --name claude2api \
  ghcr.io/yushangxiao/claude2api:latest

1. Fork the Hugging Face Space: https://huggingface.co/spaces/rclon/claude2api
2. Configure your environment variables in the Settings tab.
3. The Space will automatically deploy the Docker image.

Note: In Hugging Face, the /v1 path might be blocked; use /hf/v1 instead.

If a config.yaml file exists in the application's root directory, it will be used instead of environment variables. This file allows for structured configuration of sessions, server settings, and API keys.

# Sessions configuration
sessions:
  - sessionKey: "sk-ant-sid01-xxxx"
    orgID: ""
  - sessionKey: "sk-ant-sid01-yyyy"
    orgID: ""

# Server address
address: "0.0.0.0:8080"

# API authentication key
apiKey: "123"

# Other configuration options...
chatDelete: true
maxChatHistoryLength: 10000
noRolePrefix: false
promptDisableArtifacts: false
enableMirrorApi: false
mirrorApiPrefix: ""

If a config.yaml file exists in the application root, it will be used instead of environment variables. This file allows you to define sessions, server addresses, and other operational settings.

# Sessions configuration
sessions:
  - sessionKey: "sk-ant-sid01-xxxx"
    orgID: ""
  - sessionKey: "sk-ant-sid01-yyyy"
    orgID: ""

# Server address
address: "0.0.0.0:8080"

# API authentication key
apiKey: "123"

# Other configuration options...
chatDelete: true
maxChatHistoryLength: 10000
noRolePrefix: false
promptDisableArtifacts: false
enableMirrorApi: false
mirrorApiPrefix: ""

The application is a Go-based service that initializes a Gin web server, loads configuration, and sets up API routes. By default, the server runs on the address specified in the configuration (typically 0.0.0.0:8080).

go run main.go

Claude2Api supports image recognition. Send an array of content objects to the /v1/chat/completions endpoint, including a type: "image_url" object with a base64 encoded image.

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "claude-3-7-sonnet-20250219",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "这张图片里有什么？"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,..."
            }
          }
        ]
      }
    ]
  }'

Claude2Api supports the OpenAI-compatible /v1/chat/completions endpoint. You must include your configured APIKEY in the Authorization header as a Bearer token.

# Standard Chat Completion
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "claude-3-7-sonnet-20250219",
    "messages": [
      {
        "role": "user",
        "content": "Hello, Claude!"
      }
    ],
    "stream": true
  }'

Send a POST request to /v1/chat/completions following the OpenAI API format to interact with Claude.

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "claude-3-7-sonnet-20250219",
    "messages": [
      {
        "role": "user",
        "content": "你好，Claude！"
      }
    ],
    "stream": true
  }'

To access the API, include your configured APIKEY in the Authorization header using the Bearer scheme.

Authorization: Bearer YOUR_API_KEY