### YAML Configuration Example

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Example configuration file (config.yaml) for Claude2API. This file can be used instead of environment variables for configuration.

```yaml
# 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: ""
```

--------------------------------

### Docker Compose Up Command

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Command to start the services defined in your docker-compose.yml file.

```bash
docker-compose up -d
```

--------------------------------

### Environment Variable Configuration

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Configure the service runtime parameters using environment variables before starting the binary.

```bash
export SESSIONS=sk-ant-sid01-your-first-key,sk-ant-sid01-your-second-key
export APIKEY=your-api-authentication-key

export ADDRESS=0.0.0.0:8080              # Server bind address
export PROXY=http://127.0.0.1:2080       # HTTP proxy for Claude requests
export CHAT_DELETE=true                   # Auto-delete conversations after use
export MAX_CHAT_HISTORY_LENGTH=10000      # Max chars before using file attachment
export NO_ROLE_PREFIX=false               # Disable role prefixes in prompts
export PROMPT_DISABLE_ARTIFACTS=false     # Disable Claude's artifact wrapping
export ENABLE_MIRROR_API=false            # Enable direct session key usage
export MIRROR_API_PREFIX=/mirror          # Prefix for mirror API routes

./claude2api
```

--------------------------------

### Manage Docker Compose Services

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Commands to start, monitor, and stop the service using Docker Compose.

```bash
# Start with Docker Compose
docker-compose up -d

# View logs
docker-compose logs -f

# Stop service
docker-compose down
```

--------------------------------

### GET /v1/models

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Retrieves a list of all available Claude models.

```APIDOC
## GET /v1/models

### Description
Retrieve the list of available Claude models supported by the API, including both standard and thinking-enabled variants.

### Method
GET

### Endpoint
http://localhost:8080/v1/models

### Response
#### Success Response (200)
- **data** (array) - List of model objects containing model IDs
```

--------------------------------

### GET /health

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Verifies the API service is running.

```APIDOC
## GET /health

### Description
Simple health check endpoint to verify the API service is running and responsive.

### Method
GET

### Endpoint
http://localhost:8080/health

### Response
#### Success Response (200)
- **status** (string) - Should return 'ok'
```

--------------------------------

### Direct Deployment (Build and Run)

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Deploy Claude2Api by building from source. This involves cloning the repository, setting up environment variables, building the binary, and running the executable.

```bash
# Clone the repository
git clone https://github.com/yushangxiao/claude2api.git
cd claude2api
cp .env.example .env  
vim .env  
# Build the binary
go build -o claude2api .

./claude2api
```

--------------------------------

### HuggingFace-Compatible Routes

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Use these routes when deploying on platforms like HuggingFace Spaces where standard /v1 paths might be restricted.

```bash
curl -X POST http://localhost:8080/hf/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {
        "role": "user",
        "content": "Hello, Claude!"
      }
    ],
    "stream": false
  }'

curl -X GET http://localhost:8080/hf/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"
```

--------------------------------

### Deploy with Docker Compose

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Use a YAML configuration file to define the service, environment variables, and health checks.

```yaml
# docker-compose.yml
version: '3'
services:
  claude2api:
    image: ghcr.io/yushangxiao/claude2api:latest
    container_name: claude2api
    ports:
      - "8080:8080"
    environment:
      - SESSIONS=sk-ant-sid01-your-key-1,sk-ant-sid01-your-key-2
      - ADDRESS=0.0.0.0:8080
      - APIKEY=your-secure-api-key
      - PROXY=http://proxy:2080
      - 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
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3
```

--------------------------------

### YAML Configuration File

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Use a config.yaml file for structured configuration, particularly useful when managing multiple session keys.

```yaml
sessions:
  - sessionKey: "sk-ant-sid01-your-first-session-key"
    orgID: ""
  - sessionKey: "sk-ant-sid01-your-second-session-key"
    orgID: "org-uuid-if-known"

address: "0.0.0.0:8080"
apiKey: "your-secure-api-key"

proxy: "http://127.0.0.1:2080"
```

--------------------------------

### List Available Models

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Retrieve a list of all supported Claude models, including standard and thinking-enabled versions.

```bash
curl -X GET http://localhost:8080/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"
```

--------------------------------

### Mirror API (Direct Session Key)

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Authenticate directly using Claude session keys. Requires ENABLE_MIRROR_API to be set to true.

```bash
curl -X POST http://localhost:8080/mirror/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-ant-sid01-your-session-key" \
  -d '{
    "model": "claude-3-7-sonnet-20250219",
    "messages": [
      {
        "role": "user",
        "content": "Hello from mirror API!"
      }
    ],
    "stream": false
  }'

curl -X POST http://localhost:8080/mirror/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-ant-sid01-your-session-key:org-uuid-here" \
  -d '{
    "model": "claude-3-7-sonnet-20250219",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'
```

--------------------------------

### Deploy Claude2Api with Docker

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Run the service using Docker with environment variables for session keys and API configuration.

```bash
# Basic Docker deployment
docker run -d \
  --name claude2api \
  -p 8080:8080 \
  -e SESSIONS=sk-ant-sid01-your-session-key \
  -e APIKEY=your-secure-api-key \
  -e CHAT_DELETE=true \
  -e MAX_CHAT_HISTORY_LENGTH=10000 \
  ghcr.io/yushangxiao/claude2api:latest
```

```bash
# Full configuration Docker deployment
docker run -d \
  --name claude2api \
  -p 8080:8080 \
  -e SESSIONS=sk-ant-sid01-key1,sk-ant-sid01-key2 \
  -e APIKEY=your-secure-api-key \
  -e PROXY=http://host.docker.internal:2080 \
  -e CHAT_DELETE=true \
  -e MAX_CHAT_HISTORY_LENGTH=10000 \
  -e NO_ROLE_PREFIX=false \
  -e PROMPT_DISABLE_ARTIFACTS=true \
  -e ENABLE_MIRROR_API=true \
  -e MIRROR_API_PREFIX=/mirror \
  --restart unless-stopped \
  ghcr.io/yushangxiao/claude2api:latest
```

--------------------------------

### Docker Compose Deployment

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Set up Claude2Api with Docker Compose. This method allows for a more structured configuration of services and environment variables.

```yaml
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 

```

--------------------------------

### Docker Deployment

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Deploy Claude2Api using Docker. Ensure to set necessary environment variables like SESSIONS and APIKEY.

```bash
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
```

--------------------------------

### POST /mirror/v1/chat/completions

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Mirror API endpoint for using direct Claude session keys.

```APIDOC
## POST /mirror/v1/chat/completions

### Description
Allows using Claude session keys directly as the API key for authentication. Supports optional organization ID in the Authorization header.

### Method
POST

### Endpoint
http://localhost:8080/mirror/v1/chat/completions

### Request Body
- **model** (string) - Required - The model ID
- **messages** (array) - Required - List of message objects
- **stream** (boolean) - Optional - Whether to stream the response
```

--------------------------------

### Execute Multi-turn Conversation Request

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Send a POST request to the chat completions endpoint including a message history array.

```bash
# Multi-turn conversation example
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": "system",
        "content": "You are a helpful coding assistant specialized in Python."
      },
      {
        "role": "user",
        "content": "How do I read a JSON file in Python?"
      },
      {
        "role": "assistant",
        "content": "You can use the json module:\n\nimport json\n\nwith open(\"data.json\", \"r\") as f:\n    data = json.load(f)"
      },
      {
        "role": "user",
        "content": "How do I handle the case where the file might not exist?"
      }
    ],
    "stream": false
  }'
```

--------------------------------

### Manage Docker Containers

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Commands for checking logs of a running Claude2Api container.

```bash
# Check container logs
docker logs -f claude2api
```

--------------------------------

### Health Check Endpoint

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Verify that the API service is running and responsive.

```bash
curl -X GET http://localhost:8080/health
```

--------------------------------

### Image Analysis with Base64 Encoding

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Perform image analysis by sending a base64-encoded image along with a text prompt. The 'content' field in the messages array should include both text and the image_url object.

```bash
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": "What objects do you see in this image? Describe them in detail."
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEASABIAAD..."
            }
          }
        ]
      }
    ],
    "stream": false
  }'
```

--------------------------------

### Image Analysis with Multiple Images

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Analyze multiple images in a single request by including multiple 'image_url' objects within the 'content' array. This is useful for comparing images or providing more context.

```bash
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": "Compare these two images and describe their differences."
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUg..."
            }
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUg..."
            }
          }
        ]
      }
    ]
  }'
```

--------------------------------

### Enable thinking mode for complex problem solving

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Use the thinking-enabled model variant to receive a step-by-step reasoning process in the response.

```bash
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-think",
    "messages": [
      {
        "role": "user",
        "content": "Solve this step by step: If a train travels 120 km in 2 hours, and then 180 km in 3 hours, what is the average speed for the entire journey?"
      }
    ],
    "stream": true
  }'
```

--------------------------------

### POST /v1/chat/completions

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Sends a chat message to the Claude model, supporting thinking mode and streaming.

```APIDOC
## POST /v1/chat/completions

### Description
Sends a chat message to the Claude model. Supports thinking mode by selecting specific models and streaming responses.

### Method
POST

### Endpoint
http://localhost:8080/v1/chat/completions

### Request Body
- **model** (string) - Required - The model ID (e.g., claude-3-7-sonnet-20250219-think)
- **messages** (array) - Required - List of message objects with role and content
- **stream** (boolean) - Optional - Whether to stream the response

### Request Example
{
  "model": "claude-3-7-sonnet-20250219-think",
  "messages": [
    {"role": "user", "content": "Solve this step by step..."}
  ],
  "stream": true
}
```

--------------------------------

### Streaming Chat Completion Request

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Initiate a streaming chat completion request by setting the 'stream' parameter to true. Responses will be received as Server-Sent Events (SSE).

```bash
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about programming"
      }
    ],
    "stream": true
  }'
```

--------------------------------

### Basic Chat Completion Request

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Use this command to send a basic chat completion request to the Claude2Api. Ensure your API key and model name are correctly specified. Set 'stream' to false for a non-streaming response.

```bash
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": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is the capital of France?"
      }
    ],
    "stream": false
  }'
```

--------------------------------

### Thinking Mode

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Enable Claude's extended thinking process for complex reasoning tasks by appending '-think' to the model name. Responses include `<think>` tags containing Claude's step-by-step reasoning before the final answer.

```APIDOC
## Using Thinking Mode

### Description
Activates an extended reasoning process for Claude models, providing step-by-step thought processes within the response. This is useful for complex problem-solving and debugging.

### How to Enable
Append `-think` to the model name when making a request to the Chat Completions endpoint.

### Example Model Name
`claude-3-opus-20240229-think`

### Response Format
Responses will include `<think>` tags containing the model's reasoning process before the final answer.

### Example Response Snippet
```xml
<think>
  The user is asking for the capital of France. I know that Paris is the capital of France. Therefore, the answer is Paris.
</think>
The capital of France is Paris.
```
```

--------------------------------

### Send Image Analysis Request

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

This cURL command demonstrates how to perform image analysis using the Claude API. It includes a text prompt and an image URL within the messages payload. Replace YOUR_API_KEY and the base64 encoded image data as needed.

```bash
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": "What\'s in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/jpeg;base64,மையில்"
            }
          }
        ]
      }
    ] 
  }'
```

--------------------------------

### Send Chat Completion Request

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Use this cURL command to send a text-based chat completion request to the Claude API. Ensure you replace YOUR_API_KEY with your actual API key and specify the desired model.

```bash
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
  }'
```

--------------------------------

### Image Analysis

Source: https://context7.com/yushangxiao/claude2api/llms.txt

Send images to Claude for analysis using base64-encoded data or URLs. The API processes images through Claude's vision capabilities and returns detailed descriptions or answers to questions about the image content.

```APIDOC
## POST /v1/chat/completions (with image analysis)

### Description
Allows sending images along with text prompts to Claude for analysis. Supports base64-encoded images and image URLs.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The Claude model to use (e.g., "claude-3-7-sonnet-20250219").
- **messages** (array) - Required - An array of message objects. For image analysis, the content can be a mix of text and image objects.
  - **role** (string) - Required - Role of the message sender (e.g., "user").
  - **content** (array) - Required - An array containing message parts.
    - **type** (string) - Required - Type of content ("text" or "image_url").
    - **text** (string) - Required if type is "text" - The text prompt.
    - **image_url** (object) - Required if type is "image_url" - Object containing the image URL.
      - **url** (string) - Required - The URL of the image, can be a data URI (e.g., "data:image/jpeg;base64,...").
- **stream** (boolean) - Optional - Whether to stream the response. Defaults to false.

### Request Example (Base64 Image)
```json
{
  "model": "claude-3-7-sonnet-20250219",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What objects do you see in this image? Describe them in detail."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEASABIAAD..."
          }
        }
      ]
    }
  ],
  "stream": false
}
```

### Request Example (Multiple Images)
```json
{
  "model": "claude-3-7-sonnet-20250219",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Compare these two images and describe their differences."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUg..."
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUg..."
          }
        }
      ]
    }
  ]
}
```

### Response
#### Success Response (200)
Similar to the Chat Completions response, with the assistant's response detailing the image analysis.
- **id** (string) - Unique identifier for the completion.
- **object** (string) - Type of object returned (e.g., "chat.completion").
- **created** (integer) - Timestamp of creation.
- **model** (string) - The model used for the completion.
- **choices** (array) - An array of completion choices.
  - **index** (integer) - Index of the choice.
  - **message** (object) - The message content.
    - **role** (string) - Role of the message sender (e.g., "assistant").
    - **content** (string) - The response text describing the image analysis.
  - **finish_reason** (string) - The reason the model stopped generating tokens.

### Response Example (Non-streaming)
```json
{
  "id": "uuid-here",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "claude-3-7-sonnet-20250219",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The image contains a red car parked on a street. There are trees in the background."
      },
      "finish_reason": "stop"
    }
  ]
}
```
```

--------------------------------

### Chat Completions Endpoint

Source: https://context7.com/yushangxiao/claude2api/llms.txt

The primary endpoint for sending messages to Claude models using OpenAI-compatible format. Supports both streaming and non-streaming responses, multiple message types, and various Claude models including thinking-enabled variants.

```APIDOC
## POST /v1/chat/completions

### Description
Sends messages to Claude models using an OpenAI-compatible format. Supports streaming and non-streaming responses.

### Method
POST

### Endpoint
/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The Claude model to use (e.g., "claude-3-7-sonnet-20250219").
- **messages** (array) - Required - An array of message objects, each with a "role" (system, user, assistant) and "content".
- **stream** (boolean) - Optional - Whether to stream the response. Defaults to false.

### Request Example (Non-streaming)
```json
{
  "model": "claude-3-7-sonnet-20250219",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is the capital of France?"
    }
  ],
  "stream": false
}
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the completion.
- **object** (string) - Type of object returned (e.g., "chat.completion").
- **created** (integer) - Timestamp of creation.
- **model** (string) - The model used for the completion.
- **choices** (array) - An array of completion choices.
  - **index** (integer) - Index of the choice.
  - **message** (object) - The message content.
    - **role** (string) - Role of the message sender (e.g., "assistant").
    - **content** (string) - The response text.
  - **finish_reason** (string) - The reason the model stopped generating tokens.

### Response Example (Non-streaming)
```json
{
  "id": "uuid-here",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "claude-3-7-sonnet-20250219",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ]
}
```

### Request Example (Streaming)
```json
{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about programming"
    }
  ],
  "stream": true
}
```

### Response Example (Streaming SSE)
```
data: {"id":"uuid","object":"chat.completion.chunk","created":1234567890,"model":"claude-3-7-sonnet-20250219","choices":[{"index":0,"delta":{"content":"Code"},"logprobs":null,"finish_reason":null}]}
data: {"id":"uuid","object":"chat.completion.chunk","created":1234567890,"model":"claude-3-7-sonnet-20250219","choices":[{"index":0,"delta":{"content":" flows"},"logprobs":null,"finish_reason":null}]}
...
data: [DONE]
```
```

--------------------------------

### API Authentication Header

Source: https://github.com/yushangxiao/claude2api/blob/main/README.md

Include your API key in the request header for authentication when interacting with the Claude2Api.

```http
Authorization: Bearer YOUR_API_KEY
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.