Claude (Anthropic Protocol)

1. Overview

Claude is a large language model developed by Anthropic, possessing strong conversation and writing capabilities. It can understand context, generate coherent text, write code, and excels at logical reasoning and analysis. It emphasizes safety and ethical guidelines and will clearly identify itself as an AI assistant. It supports multilingual communication and can handle complex tasks and long conversations.

Compliance with Anthropic API

This API complies with the Anthropic Claude interface format specification and supports all official parameters.

Documentation Reference

This document lists only a subset of parameters. For a detailed list of parameters, please refer to the official documentation.

1.1 Supported model IDs

• claude-opus-4-7
• claude-opus-4-6
• claude-opus-4-5
• claude-opus-4
• claude-sonnet-4-6
• claude-sonnet-4-5
• claude-sonnet-4
• claude-haiku-4-5

2. Request Instructions

Request Method:

POST

Request URL:

https://api.exchangetoken.ai/v1/messages

3. Request Parameters

3.1 Header Parameters

Parameter Name	Type	Required	Description	Example
Content-Type	string	Yes	Set request header type, must be application/json.	application/json
Accept	string	Yes	Set response type, recommended to unify as application/json.	application/json
x-api-key	string	Yes	API_KEY required for authentication, format: $YOUR_API_KEY.	$YOUR_API_KEY

3.2 Body Parameters (application/json)

Parameter Name	Type	Required	Description	Example
model	string	Yes	The model ID to use. See the available versions listed in Overview, e.g., claude-opus-4-7.	claude-opus-4-7
messages	array	Yes	List of chat messages, compatible with Anthropic format. Each object in the array contains role and content.	[{"role": "user", "content": "Hello"}]
message.role	string	Yes	Message role, optional values: user, assistant.	user
message.content	string	Yes	The specific content of the message.	Hello, please tell me a joke.
system	string	No	System prompt.	You are a friendly AI assistant.
temperature	number	No	Sampling temperature, value 0~2. Higher values are more random; lower values are more concentrated and deterministic.	0.7
top_p	number	No	Another way to adjust sampling distribution, value 0~1. Usually choose between this and temperature.	0.9
stream	boolean	No	Whether to enable streaming output. When set to true, returns stream data similar to ChatGPT.	false
max_tokens	integer	Yes	Maximum token count generated per response, limited by model context length.	8192

Complete Code Examples

1. Basic Chat

cURL

curl -X POST "https://api.exchangetoken.ai/v1/messages" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "system": [
      {
        "type": "text",
        "text": "You are a friendly AI assistant"
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Hello, please give me a brief introduction to quantum mechanics"
          }
        ]
      }
    ],
    "temperature": 0.7,
    "max_tokens": 1000
  }'

Python (requests)

import requests
import json

url = "https://api.exchangetoken.ai/v1/messages"
headers = {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "model": "claude-opus-4-7",
    "system": [
        {
            "type": "text",
            "text": "You are a friendly AI assistant"
        }
    ],
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Hello, please give me a brief introduction to quantum mechanics"
                }
            ]
        }
    ],
    "temperature": 0.7,
    "max_tokens": 1000
}

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

2. Thinking Mode

cURL

curl -X POST "https://api.exchangetoken.ai/v1/messages" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 2048,
    "thinking": {
      "type": "enabled",
      "budget_tokens": 1024
    },
    "messages": [
      {
        "role": "user",
        "content": "Explain how quantum entanglement works."
      }
    ]
  }'

Python (requests)

import requests
import json

url = "https://api.exchangetoken.ai/v1/messages"
headers = {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "model": "claude-sonnet-4-6",
    "max_tokens": 2048,
    "thinking": {
        "type": "enabled",
        "budget_tokens": 1024
    },
    "messages": [
        {
            "role": "user",
            "content": "Explain how quantum entanglement works."
        }
    ]
}

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

3. Streaming Response

cURL

curl -X POST "https://api.exchangetoken.ai/v1/messages" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-7",
    "messages": [
      {
        "role": "user",
        "content": "Tell me a short story"
      }
    ],
    "stream": true,
    "max_tokens": 1024
  }'

Python (requests)

import requests
import json

url = "https://api.exchangetoken.ai/v1/messages"
headers = {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "model": "claude-opus-4-7",
    "messages": [
        {
            "role": "user",
            "content": "Tell me a short story"
        }
    ],
    "stream": True,
    "max_tokens": 1024
}

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

for line in response.iter_lines():
    if line:
        print(line.decode('utf-8'))