Last Update: 2025/3/26

Anthropic Messages API

The Anthropic Messages API allows you to generate conversational responses using Anthropic's language models. This document provides an overview of the API endpoints, request parameters, and response structure.

Endpoint

POST https://platform.llmprovider.ai/v1/messages

Request Headers

Header	Value
x-api-key	YOUR_API_KEY
anthropic-version	2023-06-01
Content-Type	application/json

Request Body

The request body should be a JSON object with the following parameters:

Parameter	Type	Description
model	string	The model to use (e.g., claude-3-opus-20240229).
messages	string[]	A list of message objects.
messages.role	string	The role of the message sender (user, assistant).
messages.content	string	The content of the message.
max_tokens	integer	(Optional) The maximum number of tokens to generate before stopping.
metadata	object	(Optional) An object describing metadata about the request.
stop_sequences	array	(Optional) Custom text sequences that will cause the model to stop generating.
stream	boolean	(Optional)Whether to incrementally stream the response using server-sent events.
system	string	(Optional) A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role.
temperature	number	(Optional) Amount of randomness injected into the response, between 0 and 1.
tool_choices	object	(Optional) How the model should use the provided tools. The model can use a specific tool, any available tool, or decide by itself.
tools	object[]	(Optional) Definitions of tools that the model may use.
top_k	number	(Optional) Only sample from the top K options for each subsequent token. Required range: x > 0
top_p	number	(Optional) Use nucleus sampling. Required range:0 < x < 1

Example Request

{
  "model": "claude-3-5-sonnet-20241022",
  "messages": [
    {
      "role": "user",
      "content": "Hello, Claude!"
    }
  ],
  "max_tokens": 1024
}

Response Body

The response body will be a JSON object containing the generated response and metadata.

Field	Type	Description
id	string	Unique identifier for the message.
model	string	The model that handled the request.
role	string	Conversational role of the generated message. This will always be assistant.
content	array	Array of content objects containing the response.
content.type	string	The type of content, usually text.
content.text	string	The text content of the response.
stop_reason	string	The reason for stopping the response generation.
stop_sequences	string	The stop sequences that caused the model to stop generating.
type	string	The type of object returned, usually message.
usage	object	Token usage statistics for the request.

Example Response

{
  "id": "msg_123abc",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "model": "claude-3-5-sonnet-20241022",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 8
  }
}

Example Request

Shell

curl -X POST https://platform.llmprovider.ai/v1/messages \
-H "x-api-key: $YOUR_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
  "model": "claude-3-5-sonnet-20241022",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

nodejs

const axios = require('axios');
const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/messages';

const data = {
    model: 'claude-3-5-sonnet-20241022',
    messages: [
        {
            role: 'user',
            content: 'Hello!'
        }
    ]
};

const headers = {
    'x-api-key': apiKey,
    'anthropic-version': '2023-06-01',
    'Content-Type': 'application/json'
};

axios.post(url, data, { headers })
.then(response => {
    console.log('Response:', response.data);
})
.catch(error => {
    console.error('Error:', error);
});

python

import requests
import json

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/messages'

headers = {
    'x-api-key': api_key,
    'anthropic-version': '2023-06-01',
    'Content-Type': 'application/json'
}

data = {
    'model': 'claude-3-5-sonnet-20241022',
    'messages': [
        {
            'role': 'user',
            'content': 'Hello!'
        }
    ]
}

response = requests.post(url, headers=headers, data=json.dumps(data))

if response.status_code == 200:
    print('Response:', response.json())
else:
    print('Error:', response.status_code, response.text)

For more details, refer to the Anthropic API documentation.