Claude format

Create Message

curl --request POST \
  --url https://api.example.com/v1/messages \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: <x-api-key>' \
  --header 'anthropic-version: <anthropic-version>' \
  --data '
{
  "max_tokens": 123,
  "model": "<string>",
  "messages": [
    {
      "content": {}
    }
  ],
  "top_p": 123,
  "top_k": 123,
  "stop_sequences": [
    "<string>"
  ],
  "tool_choice": {},
  "cache_control": {
    "type": "<string>",
    "ttl": "<string>"
  },
  "inference_geo": "<string>",
  "output_config": {
    "effort": "<string>",
    "format": {
      "schema": [
        [
          [
            {}
          ]
        ]
      ],
      "type": "<string>"
    }
  },
  "service_tier": "<string>",
  "system": {},
  "temperature": 123,
  "stream": true,
  "thinking": {
    "budget_tokens": 123,
    "type": "<string>",
    "display": "<string>"
  },
  "tools": [
    {
      "input_schema": [
        [
          [
            {}
          ]
        ]
      ],
      "allowed_callers": [
        "<string>"
      ],
      "cache_control": {
        "type": "<string>",
        "ttl": "<string>"
      },
      "defer_loading": true,
      "eager_input_streaming": true,
      "input_examples": [
        {
          "key": {}
        }
      ],
      "name": "<string>",
      "description": "<string>",
      "type": "<string>",
      "strict": true
    }
  ],
  "metadata": {
    "user_id": "<string>"
  },
  "container": "<string>"
}
'

import requests

url = "https://api.example.com/v1/messages"

payload = {
    "max_tokens": 123,
    "model": "<string>",
    "messages": [{ "content": {} }],
    "top_p": 123,
    "top_k": 123,
    "stop_sequences": ["<string>"],
    "tool_choice": {},
    "cache_control": {
        "type": "<string>",
        "ttl": "<string>"
    },
    "inference_geo": "<string>",
    "output_config": {
        "effort": "<string>",
        "format": {
            "schema": [[[{}]]],
            "type": "<string>"
        }
    },
    "service_tier": "<string>",
    "system": {},
    "temperature": 123,
    "stream": True,
    "thinking": {
        "budget_tokens": 123,
        "type": "<string>",
        "display": "<string>"
    },
    "tools": [
        {
            "input_schema": [[[{}]]],
            "allowed_callers": ["<string>"],
            "cache_control": {
                "type": "<string>",
                "ttl": "<string>"
            },
            "defer_loading": True,
            "eager_input_streaming": True,
            "input_examples": [{ "key": {} }],
            "name": "<string>",
            "description": "<string>",
            "type": "<string>",
            "strict": True
        }
    ],
    "metadata": { "user_id": "<string>" },
    "container": "<string>"
}
headers = {
    "anthropic-version": "<anthropic-version>",
    "X-Api-Key": "<x-api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'anthropic-version': '<anthropic-version>',
    'X-Api-Key': '<x-api-key>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    max_tokens: 123,
    model: '<string>',
    messages: [{content: {}}],
    top_p: 123,
    top_k: 123,
    stop_sequences: ['<string>'],
    tool_choice: {},
    cache_control: {type: '<string>', ttl: '<string>'},
    inference_geo: '<string>',
    output_config: {effort: '<string>', format: {schema: [[[{}]]], type: '<string>'}},
    service_tier: '<string>',
    system: {},
    temperature: 123,
    stream: true,
    thinking: {budget_tokens: 123, type: '<string>', display: '<string>'},
    tools: [
      {
        input_schema: [[[{}]]],
        allowed_callers: ['<string>'],
        cache_control: {type: '<string>', ttl: '<string>'},
        defer_loading: true,
        eager_input_streaming: true,
        input_examples: [{key: {}}],
        name: '<string>',
        description: '<string>',
        type: '<string>',
        strict: true
      }
    ],
    metadata: {user_id: '<string>'},
    container: '<string>'
  })
};

fetch('https://api.example.com/v1/messages', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/v1/messages",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'max_tokens' => 123,
    'model' => '<string>',
    'messages' => [
        [
                'content' => [
                                
                ]
        ]
    ],
    'top_p' => 123,
    'top_k' => 123,
    'stop_sequences' => [
        '<string>'
    ],
    'tool_choice' => [
        
    ],
    'cache_control' => [
        'type' => '<string>',
        'ttl' => '<string>'
    ],
    'inference_geo' => '<string>',
    'output_config' => [
        'effort' => '<string>',
        'format' => [
                'schema' => [
                                [
                                                                [
                                                                                                                                [
                                                                                                                                                                                                                                                                
                                                                                                                                ]
                                                                ]
                                ]
                ],
                'type' => '<string>'
        ]
    ],
    'service_tier' => '<string>',
    'system' => [
        
    ],
    'temperature' => 123,
    'stream' => true,
    'thinking' => [
        'budget_tokens' => 123,
        'type' => '<string>',
        'display' => '<string>'
    ],
    'tools' => [
        [
                'input_schema' => [
                                [
                                                                [
                                                                                                                                [
                                                                                                                                                                                                                                                                
                                                                                                                                ]
                                                                ]
                                ]
                ],
                'allowed_callers' => [
                                '<string>'
                ],
                'cache_control' => [
                                'type' => '<string>',
                                'ttl' => '<string>'
                ],
                'defer_loading' => true,
                'eager_input_streaming' => true,
                'input_examples' => [
                                [
                                                                'key' => [
                                                                                                                                
                                                                ]
                                ]
                ],
                'name' => '<string>',
                'description' => '<string>',
                'type' => '<string>',
                'strict' => true
        ]
    ],
    'metadata' => [
        'user_id' => '<string>'
    ],
    'container' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-Api-Key: <x-api-key>",
    "anthropic-version: <anthropic-version>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/v1/messages"

	payload := strings.NewReader("{\n  \"max_tokens\": 123,\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": {}\n    }\n  ],\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"tool_choice\": {},\n  \"cache_control\": {\n    \"type\": \"<string>\",\n    \"ttl\": \"<string>\"\n  },\n  \"inference_geo\": \"<string>\",\n  \"output_config\": {\n    \"effort\": \"<string>\",\n    \"format\": {\n      \"schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"type\": \"<string>\"\n    }\n  },\n  \"service_tier\": \"<string>\",\n  \"system\": {},\n  \"temperature\": 123,\n  \"stream\": true,\n  \"thinking\": {\n    \"budget_tokens\": 123,\n    \"type\": \"<string>\",\n    \"display\": \"<string>\"\n  },\n  \"tools\": [\n    {\n      \"input_schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"allowed_callers\": [\n        \"<string>\"\n      ],\n      \"cache_control\": {\n        \"type\": \"<string>\",\n        \"ttl\": \"<string>\"\n      },\n      \"defer_loading\": true,\n      \"eager_input_streaming\": true,\n      \"input_examples\": [\n        {\n          \"key\": {}\n        }\n      ],\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"type\": \"<string>\",\n      \"strict\": true\n    }\n  ],\n  \"metadata\": {\n    \"user_id\": \"<string>\"\n  },\n  \"container\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("anthropic-version", "<anthropic-version>")
	req.Header.Add("X-Api-Key", "<x-api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/v1/messages")
  .header("anthropic-version", "<anthropic-version>")
  .header("X-Api-Key", "<x-api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"max_tokens\": 123,\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": {}\n    }\n  ],\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"tool_choice\": {},\n  \"cache_control\": {\n    \"type\": \"<string>\",\n    \"ttl\": \"<string>\"\n  },\n  \"inference_geo\": \"<string>\",\n  \"output_config\": {\n    \"effort\": \"<string>\",\n    \"format\": {\n      \"schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"type\": \"<string>\"\n    }\n  },\n  \"service_tier\": \"<string>\",\n  \"system\": {},\n  \"temperature\": 123,\n  \"stream\": true,\n  \"thinking\": {\n    \"budget_tokens\": 123,\n    \"type\": \"<string>\",\n    \"display\": \"<string>\"\n  },\n  \"tools\": [\n    {\n      \"input_schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"allowed_callers\": [\n        \"<string>\"\n      ],\n      \"cache_control\": {\n        \"type\": \"<string>\",\n        \"ttl\": \"<string>\"\n      },\n      \"defer_loading\": true,\n      \"eager_input_streaming\": true,\n      \"input_examples\": [\n        {\n          \"key\": {}\n        }\n      ],\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"type\": \"<string>\",\n      \"strict\": true\n    }\n  ],\n  \"metadata\": {\n    \"user_id\": \"<string>\"\n  },\n  \"container\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/messages")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["anthropic-version"] = '<anthropic-version>'
request["X-Api-Key"] = '<x-api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"max_tokens\": 123,\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": {}\n    }\n  ],\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"tool_choice\": {},\n  \"cache_control\": {\n    \"type\": \"<string>\",\n    \"ttl\": \"<string>\"\n  },\n  \"inference_geo\": \"<string>\",\n  \"output_config\": {\n    \"effort\": \"<string>\",\n    \"format\": {\n      \"schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"type\": \"<string>\"\n    }\n  },\n  \"service_tier\": \"<string>\",\n  \"system\": {},\n  \"temperature\": 123,\n  \"stream\": true,\n  \"thinking\": {\n    \"budget_tokens\": 123,\n    \"type\": \"<string>\",\n    \"display\": \"<string>\"\n  },\n  \"tools\": [\n    {\n      \"input_schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"allowed_callers\": [\n        \"<string>\"\n      ],\n      \"cache_control\": {\n        \"type\": \"<string>\",\n        \"ttl\": \"<string>\"\n      },\n      \"defer_loading\": true,\n      \"eager_input_streaming\": true,\n      \"input_examples\": [\n        {\n          \"key\": {}\n        }\n      ],\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"type\": \"<string>\",\n      \"strict\": true\n    }\n  ],\n  \"metadata\": {\n    \"user_id\": \"<string>\"\n  },\n  \"container\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "stop_reason": "<string>",
  "stop_sequence": "<string>",
  "stop_details": {
    "type": "<string>",
    "category": "<string>",
    "explanation": "<string>"
  },
  "id": "<string>",
  "type": "<string>",
  "role": "<string>",
  "content": [
    {}
  ],
  "model": "<string>",
  "container": {
    "expires_at": "<string>",
    "id": "<string>"
  },
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 123,
      "ephemeral_1h_input_tokens": 123
    },
    "inference_geo": "<string>",
    "output_tokens_details": {
      "thinking_tokens": 123
    },
    "server_tool_use": {
      "web_search_requests": 123,
      "web_fetch_requests": 123
    },
    "service_tier": "<string>"
  }
}

POST

messages

Create Message

curl --request POST \
  --url https://api.example.com/v1/messages \
  --header 'Content-Type: application/json' \
  --header 'X-Api-Key: <x-api-key>' \
  --header 'anthropic-version: <anthropic-version>' \
  --data '
{
  "max_tokens": 123,
  "model": "<string>",
  "messages": [
    {
      "content": {}
    }
  ],
  "top_p": 123,
  "top_k": 123,
  "stop_sequences": [
    "<string>"
  ],
  "tool_choice": {},
  "cache_control": {
    "type": "<string>",
    "ttl": "<string>"
  },
  "inference_geo": "<string>",
  "output_config": {
    "effort": "<string>",
    "format": {
      "schema": [
        [
          [
            {}
          ]
        ]
      ],
      "type": "<string>"
    }
  },
  "service_tier": "<string>",
  "system": {},
  "temperature": 123,
  "stream": true,
  "thinking": {
    "budget_tokens": 123,
    "type": "<string>",
    "display": "<string>"
  },
  "tools": [
    {
      "input_schema": [
        [
          [
            {}
          ]
        ]
      ],
      "allowed_callers": [
        "<string>"
      ],
      "cache_control": {
        "type": "<string>",
        "ttl": "<string>"
      },
      "defer_loading": true,
      "eager_input_streaming": true,
      "input_examples": [
        {
          "key": {}
        }
      ],
      "name": "<string>",
      "description": "<string>",
      "type": "<string>",
      "strict": true
    }
  ],
  "metadata": {
    "user_id": "<string>"
  },
  "container": "<string>"
}
'

import requests

url = "https://api.example.com/v1/messages"

payload = {
    "max_tokens": 123,
    "model": "<string>",
    "messages": [{ "content": {} }],
    "top_p": 123,
    "top_k": 123,
    "stop_sequences": ["<string>"],
    "tool_choice": {},
    "cache_control": {
        "type": "<string>",
        "ttl": "<string>"
    },
    "inference_geo": "<string>",
    "output_config": {
        "effort": "<string>",
        "format": {
            "schema": [[[{}]]],
            "type": "<string>"
        }
    },
    "service_tier": "<string>",
    "system": {},
    "temperature": 123,
    "stream": True,
    "thinking": {
        "budget_tokens": 123,
        "type": "<string>",
        "display": "<string>"
    },
    "tools": [
        {
            "input_schema": [[[{}]]],
            "allowed_callers": ["<string>"],
            "cache_control": {
                "type": "<string>",
                "ttl": "<string>"
            },
            "defer_loading": True,
            "eager_input_streaming": True,
            "input_examples": [{ "key": {} }],
            "name": "<string>",
            "description": "<string>",
            "type": "<string>",
            "strict": True
        }
    ],
    "metadata": { "user_id": "<string>" },
    "container": "<string>"
}
headers = {
    "anthropic-version": "<anthropic-version>",
    "X-Api-Key": "<x-api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'anthropic-version': '<anthropic-version>',
    'X-Api-Key': '<x-api-key>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    max_tokens: 123,
    model: '<string>',
    messages: [{content: {}}],
    top_p: 123,
    top_k: 123,
    stop_sequences: ['<string>'],
    tool_choice: {},
    cache_control: {type: '<string>', ttl: '<string>'},
    inference_geo: '<string>',
    output_config: {effort: '<string>', format: {schema: [[[{}]]], type: '<string>'}},
    service_tier: '<string>',
    system: {},
    temperature: 123,
    stream: true,
    thinking: {budget_tokens: 123, type: '<string>', display: '<string>'},
    tools: [
      {
        input_schema: [[[{}]]],
        allowed_callers: ['<string>'],
        cache_control: {type: '<string>', ttl: '<string>'},
        defer_loading: true,
        eager_input_streaming: true,
        input_examples: [{key: {}}],
        name: '<string>',
        description: '<string>',
        type: '<string>',
        strict: true
      }
    ],
    metadata: {user_id: '<string>'},
    container: '<string>'
  })
};

fetch('https://api.example.com/v1/messages', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/v1/messages",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'max_tokens' => 123,
    'model' => '<string>',
    'messages' => [
        [
                'content' => [
                                
                ]
        ]
    ],
    'top_p' => 123,
    'top_k' => 123,
    'stop_sequences' => [
        '<string>'
    ],
    'tool_choice' => [
        
    ],
    'cache_control' => [
        'type' => '<string>',
        'ttl' => '<string>'
    ],
    'inference_geo' => '<string>',
    'output_config' => [
        'effort' => '<string>',
        'format' => [
                'schema' => [
                                [
                                                                [
                                                                                                                                [
                                                                                                                                                                                                                                                                
                                                                                                                                ]
                                                                ]
                                ]
                ],
                'type' => '<string>'
        ]
    ],
    'service_tier' => '<string>',
    'system' => [
        
    ],
    'temperature' => 123,
    'stream' => true,
    'thinking' => [
        'budget_tokens' => 123,
        'type' => '<string>',
        'display' => '<string>'
    ],
    'tools' => [
        [
                'input_schema' => [
                                [
                                                                [
                                                                                                                                [
                                                                                                                                                                                                                                                                
                                                                                                                                ]
                                                                ]
                                ]
                ],
                'allowed_callers' => [
                                '<string>'
                ],
                'cache_control' => [
                                'type' => '<string>',
                                'ttl' => '<string>'
                ],
                'defer_loading' => true,
                'eager_input_streaming' => true,
                'input_examples' => [
                                [
                                                                'key' => [
                                                                                                                                
                                                                ]
                                ]
                ],
                'name' => '<string>',
                'description' => '<string>',
                'type' => '<string>',
                'strict' => true
        ]
    ],
    'metadata' => [
        'user_id' => '<string>'
    ],
    'container' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-Api-Key: <x-api-key>",
    "anthropic-version: <anthropic-version>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/v1/messages"

	payload := strings.NewReader("{\n  \"max_tokens\": 123,\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": {}\n    }\n  ],\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"tool_choice\": {},\n  \"cache_control\": {\n    \"type\": \"<string>\",\n    \"ttl\": \"<string>\"\n  },\n  \"inference_geo\": \"<string>\",\n  \"output_config\": {\n    \"effort\": \"<string>\",\n    \"format\": {\n      \"schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"type\": \"<string>\"\n    }\n  },\n  \"service_tier\": \"<string>\",\n  \"system\": {},\n  \"temperature\": 123,\n  \"stream\": true,\n  \"thinking\": {\n    \"budget_tokens\": 123,\n    \"type\": \"<string>\",\n    \"display\": \"<string>\"\n  },\n  \"tools\": [\n    {\n      \"input_schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"allowed_callers\": [\n        \"<string>\"\n      ],\n      \"cache_control\": {\n        \"type\": \"<string>\",\n        \"ttl\": \"<string>\"\n      },\n      \"defer_loading\": true,\n      \"eager_input_streaming\": true,\n      \"input_examples\": [\n        {\n          \"key\": {}\n        }\n      ],\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"type\": \"<string>\",\n      \"strict\": true\n    }\n  ],\n  \"metadata\": {\n    \"user_id\": \"<string>\"\n  },\n  \"container\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("anthropic-version", "<anthropic-version>")
	req.Header.Add("X-Api-Key", "<x-api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/v1/messages")
  .header("anthropic-version", "<anthropic-version>")
  .header("X-Api-Key", "<x-api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"max_tokens\": 123,\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": {}\n    }\n  ],\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"tool_choice\": {},\n  \"cache_control\": {\n    \"type\": \"<string>\",\n    \"ttl\": \"<string>\"\n  },\n  \"inference_geo\": \"<string>\",\n  \"output_config\": {\n    \"effort\": \"<string>\",\n    \"format\": {\n      \"schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"type\": \"<string>\"\n    }\n  },\n  \"service_tier\": \"<string>\",\n  \"system\": {},\n  \"temperature\": 123,\n  \"stream\": true,\n  \"thinking\": {\n    \"budget_tokens\": 123,\n    \"type\": \"<string>\",\n    \"display\": \"<string>\"\n  },\n  \"tools\": [\n    {\n      \"input_schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"allowed_callers\": [\n        \"<string>\"\n      ],\n      \"cache_control\": {\n        \"type\": \"<string>\",\n        \"ttl\": \"<string>\"\n      },\n      \"defer_loading\": true,\n      \"eager_input_streaming\": true,\n      \"input_examples\": [\n        {\n          \"key\": {}\n        }\n      ],\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"type\": \"<string>\",\n      \"strict\": true\n    }\n  ],\n  \"metadata\": {\n    \"user_id\": \"<string>\"\n  },\n  \"container\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/v1/messages")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["anthropic-version"] = '<anthropic-version>'
request["X-Api-Key"] = '<x-api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"max_tokens\": 123,\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": {}\n    }\n  ],\n  \"top_p\": 123,\n  \"top_k\": 123,\n  \"stop_sequences\": [\n    \"<string>\"\n  ],\n  \"tool_choice\": {},\n  \"cache_control\": {\n    \"type\": \"<string>\",\n    \"ttl\": \"<string>\"\n  },\n  \"inference_geo\": \"<string>\",\n  \"output_config\": {\n    \"effort\": \"<string>\",\n    \"format\": {\n      \"schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"type\": \"<string>\"\n    }\n  },\n  \"service_tier\": \"<string>\",\n  \"system\": {},\n  \"temperature\": 123,\n  \"stream\": true,\n  \"thinking\": {\n    \"budget_tokens\": 123,\n    \"type\": \"<string>\",\n    \"display\": \"<string>\"\n  },\n  \"tools\": [\n    {\n      \"input_schema\": [\n        [\n          [\n            {}\n          ]\n        ]\n      ],\n      \"allowed_callers\": [\n        \"<string>\"\n      ],\n      \"cache_control\": {\n        \"type\": \"<string>\",\n        \"ttl\": \"<string>\"\n      },\n      \"defer_loading\": true,\n      \"eager_input_streaming\": true,\n      \"input_examples\": [\n        {\n          \"key\": {}\n        }\n      ],\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"type\": \"<string>\",\n      \"strict\": true\n    }\n  ],\n  \"metadata\": {\n    \"user_id\": \"<string>\"\n  },\n  \"container\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "stop_reason": "<string>",
  "stop_sequence": "<string>",
  "stop_details": {
    "type": "<string>",
    "category": "<string>",
    "explanation": "<string>"
  },
  "id": "<string>",
  "type": "<string>",
  "role": "<string>",
  "content": [
    {}
  ],
  "model": "<string>",
  "container": {
    "expires_at": "<string>",
    "id": "<string>"
  },
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 123,
      "ephemeral_1h_input_tokens": 123
    },
    "inference_geo": "<string>",
    "output_tokens_details": {
      "thinking_tokens": 123
    },
    "server_tool_use": {
      "web_search_requests": 123,
      "web_fetch_requests": 123
    },
    "service_tier": "<string>"
  }
}

This endpoint is compatible with the Anthropic Claude Messages protocol for creating conversation messages.

Features

Supports both streaming (SSE) and non-streaming response modes
Supports multimodal content (text, images, etc.)
Supports tool use
Supports thinking/reasoning mode configuration
Supports cache control optimization

Use cases

Suitable for scenarios requiring interaction with Claude models, including:

Single-turn or multi-turn conversations
Structured output (JSON Schema)
Tool calling and function execution
Code execution and container reuse

Authentication

Include the Authorization header in the format Bearer YOUR_API_KEY.

The Claude format endpoint also requires the anthropic-version header, e.g. 2023-06-01.

Quick example

import requests

url = "https://api.haitoken.ai/v1/messages"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
    "anthropic-version": "2023-06-01"
}
data = {
    "model": "claude-sonnet-4-0",
    "max_tokens": 1024,
    "messages": [
        {"role": "user", "content": "Hello, please introduce yourself"}
    ]
}

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

const response = await fetch('https://api.haitoken.ai/v1/messages', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
    'anthropic-version': '2023-06-01'
  },
  body: JSON.stringify({
    model: 'claude-sonnet-4-0',
    max_tokens: 1024,
    messages: [
      { role: 'user', content: 'Hello, please introduce yourself' }
    ]
  })
});

const data = await response.json();
console.log(data);

curl -X POST 'https://api.haitoken.ai/v1/messages' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -H 'anthropic-version: 2023-06-01' \
  -d '{
    "model": "claude-sonnet-4-0",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, please introduce yourself"}
    ]
  }'

Headers

anthropic-version

string

required

Example:

"2023-06-01"

X-Api-Key

string

required

Example:

"YOUR_API_KEY"

Body

application/json

max_tokens

integer

required

Maximum number of output tokens (required)

model

string

required

Model name, e.g. claude-sonnet-4-0, claude-opus-4-0, etc.

messages

object[]

required

List of messages

Show child attributes

top_p

number

Nucleus sampling, 0-1

top_k

integer

Top-K sampling

stop_sequences

string[]

Stop sequences

tool_choice

object

Tool choice configuration, can be a String or ClaudeToolChoice object

cache_control

object

Top-level cache control configuration Automatically applies a cache_control marker to the last cacheable block in the request

Show child attributes

inference_geo

string

Inference geographic region Specifies the geographic region for inference processing. If not specified, uses the workspace's default_inference_geo

output_config

object

Output configuration Configures model output format options, such as effort level and structured output format

Show child attributes

service_tier

string

Service tier Determines whether to use priority capacity (if available) or standard capacity Possible values: "auto" / "standard_only"

system

object

System instruction, can be a String or List

temperature

number

Sampling temperature, 0.0-1.0

stream

boolean

Whether to enable streaming output

thinking

object

Thinking/reasoning mode configuration

Show child attributes

tools

object[]

List of tool definitions

Show child attributes

metadata

object

Metadata

Show child attributes

container

string

Container identifier, used for cross-request container reuse (code execution tool)

Response

200 - application/json

Claude Messages API non-streaming response Reference: https://platform.claude.com/docs/en/api/messages/create

stop_reason

string

Stop reason: end_turn / max_tokens / stop_sequence / tool_use / pause_turn / refusal Always output in the message_start event (even when null)

stop_sequence

string

Stop sequence that was matched (can be null) Always output in the message_start event (even when null)

stop_details

object

Refusal stop details Structured information returned when the model refuses due to safety policy

Show child attributes

string

Message ID (msg_ prefix)

type

string

Object type, always "message"

role

string

Role, always "assistant"

content

object[]

List of response content blocks

model

string

Model name (the actual model that completed the task)

container

object

Container information Container identifier for the code execution tool, used for cross-request reuse

Show child attributes

usage

object

Usage statistics

Show child attributes

Quick start

API documentation

AI tool integration

Other

Features

Use cases

Authentication

Quick example

Headers

Body

Response

​Features

​Use cases

​Authentication

​Quick example

Headers

Body

Response

Features

Use cases

Authentication

Quick example