Tạo hoàn thành chat

Create chat completion

curl --request POST \
  --url https://api.openmodex.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>",
      "name": "<string>",
      "tool_call_id": "<string>",
      "tool_calls": [
        {
          "id": "<string>",
          "type": "function",
          "function": {
            "name": "<string>",
            "arguments": "<string>"
          }
        }
      ]
    }
  ],
  "stream": false,
  "temperature": 1,
  "top_p": 123,
  "n": 123,
  "max_tokens": 123,
  "stop": "<string>",
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "logit_bias": {},
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {}
      }
    }
  ],
  "tool_choice": "<string>",
  "response_format": {
    "type": "<string>"
  },
  "seed": 123,
  "user": "<string>",
  "routing": {
    "strategy": "<string>",
    "fallback": [
      "<string>"
    ],
    "allow_upgrade": true
  },
  "cache": {
    "enabled": true,
    "ttl": 123
  }
}
'

import requests

url = "https://api.openmodex.com/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [
        {
            "content": "<string>",
            "name": "<string>",
            "tool_call_id": "<string>",
            "tool_calls": [
                {
                    "id": "<string>",
                    "type": "function",
                    "function": {
                        "name": "<string>",
                        "arguments": "<string>"
                    }
                }
            ]
        }
    ],
    "stream": False,
    "temperature": 1,
    "top_p": 123,
    "n": 123,
    "max_tokens": 123,
    "stop": "<string>",
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "logit_bias": {},
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {}
            }
        }
    ],
    "tool_choice": "<string>",
    "response_format": { "type": "<string>" },
    "seed": 123,
    "user": "<string>",
    "routing": {
        "strategy": "<string>",
        "fallback": ["<string>"],
        "allow_upgrade": True
    },
    "cache": {
        "enabled": True,
        "ttl": 123
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [
      {
        content: '<string>',
        name: '<string>',
        tool_call_id: '<string>',
        tool_calls: [
          {
            id: '<string>',
            type: 'function',
            function: {name: '<string>', arguments: '<string>'}
          }
        ]
      }
    ],
    stream: false,
    temperature: 1,
    top_p: 123,
    n: 123,
    max_tokens: 123,
    stop: '<string>',
    frequency_penalty: 0,
    presence_penalty: 0,
    logit_bias: {},
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}}
      }
    ],
    tool_choice: '<string>',
    response_format: {type: '<string>'},
    seed: 123,
    user: '<string>',
    routing: {strategy: '<string>', fallback: ['<string>'], allow_upgrade: true},
    cache: {enabled: true, ttl: 123}
  })
};

fetch('https://api.openmodex.com/v1/chat/completions', 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.openmodex.com/v1/chat/completions",
  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([
    'model' => '<string>',
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>',
                'tool_call_id' => '<string>',
                'tool_calls' => [
                                [
                                                                'id' => '<string>',
                                                                'type' => 'function',
                                                                'function' => [
                                                                                                                                'name' => '<string>',
                                                                                                                                'arguments' => '<string>'
                                                                ]
                                ]
                ]
        ]
    ],
    'stream' => false,
    'temperature' => 1,
    'top_p' => 123,
    'n' => 123,
    'max_tokens' => 123,
    'stop' => '<string>',
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'logit_bias' => [
        
    ],
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ]
                ]
        ]
    ],
    'tool_choice' => '<string>',
    'response_format' => [
        'type' => '<string>'
    ],
    'seed' => 123,
    'user' => '<string>',
    'routing' => [
        'strategy' => '<string>',
        'fallback' => [
                '<string>'
        ],
        'allow_upgrade' => true
    ],
    'cache' => [
        'enabled' => true,
        'ttl' => 123
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.openmodex.com/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ]\n    }\n  ],\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"max_tokens\": 123,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"logit_bias\": {},\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {\n    \"type\": \"<string>\"\n  },\n  \"seed\": 123,\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"strategy\": \"<string>\",\n    \"fallback\": [\n      \"<string>\"\n    ],\n    \"allow_upgrade\": true\n  },\n  \"cache\": {\n    \"enabled\": true,\n    \"ttl\": 123\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.openmodex.com/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ]\n    }\n  ],\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"max_tokens\": 123,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"logit_bias\": {},\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {\n    \"type\": \"<string>\"\n  },\n  \"seed\": 123,\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"strategy\": \"<string>\",\n    \"fallback\": [\n      \"<string>\"\n    ],\n    \"allow_upgrade\": true\n  },\n  \"cache\": {\n    \"enabled\": true,\n    \"ttl\": 123\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.openmodex.com/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ]\n    }\n  ],\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"max_tokens\": 123,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"logit_bias\": {},\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {\n    \"type\": \"<string>\"\n  },\n  \"seed\": 123,\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"strategy\": \"<string>\",\n    \"fallback\": [\n      \"<string>\"\n    ],\n    \"allow_upgrade\": true\n  },\n  \"cache\": {\n    \"enabled\": true,\n    \"ttl\": 123\n  }\n}"

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

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "cost_usd": 123
  },
  "system_fingerprint": "<string>",
  "openmodex": {
    "request_id": "<string>",
    "model_used": "<string>",
    "provider": "<string>",
    "cache_hit": true,
    "routing_strategy": "<string>",
    "fallback_used": true,
    "latency_ms": 123
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

POST

chat

completions

Create chat completion

curl --request POST \
  --url https://api.openmodex.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>",
      "name": "<string>",
      "tool_call_id": "<string>",
      "tool_calls": [
        {
          "id": "<string>",
          "type": "function",
          "function": {
            "name": "<string>",
            "arguments": "<string>"
          }
        }
      ]
    }
  ],
  "stream": false,
  "temperature": 1,
  "top_p": 123,
  "n": 123,
  "max_tokens": 123,
  "stop": "<string>",
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "logit_bias": {},
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "<string>",
        "description": "<string>",
        "parameters": {}
      }
    }
  ],
  "tool_choice": "<string>",
  "response_format": {
    "type": "<string>"
  },
  "seed": 123,
  "user": "<string>",
  "routing": {
    "strategy": "<string>",
    "fallback": [
      "<string>"
    ],
    "allow_upgrade": true
  },
  "cache": {
    "enabled": true,
    "ttl": 123
  }
}
'

import requests

url = "https://api.openmodex.com/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [
        {
            "content": "<string>",
            "name": "<string>",
            "tool_call_id": "<string>",
            "tool_calls": [
                {
                    "id": "<string>",
                    "type": "function",
                    "function": {
                        "name": "<string>",
                        "arguments": "<string>"
                    }
                }
            ]
        }
    ],
    "stream": False,
    "temperature": 1,
    "top_p": 123,
    "n": 123,
    "max_tokens": 123,
    "stop": "<string>",
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "logit_bias": {},
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "<string>",
                "description": "<string>",
                "parameters": {}
            }
        }
    ],
    "tool_choice": "<string>",
    "response_format": { "type": "<string>" },
    "seed": 123,
    "user": "<string>",
    "routing": {
        "strategy": "<string>",
        "fallback": ["<string>"],
        "allow_upgrade": True
    },
    "cache": {
        "enabled": True,
        "ttl": 123
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [
      {
        content: '<string>',
        name: '<string>',
        tool_call_id: '<string>',
        tool_calls: [
          {
            id: '<string>',
            type: 'function',
            function: {name: '<string>', arguments: '<string>'}
          }
        ]
      }
    ],
    stream: false,
    temperature: 1,
    top_p: 123,
    n: 123,
    max_tokens: 123,
    stop: '<string>',
    frequency_penalty: 0,
    presence_penalty: 0,
    logit_bias: {},
    tools: [
      {
        type: 'function',
        function: {name: '<string>', description: '<string>', parameters: {}}
      }
    ],
    tool_choice: '<string>',
    response_format: {type: '<string>'},
    seed: 123,
    user: '<string>',
    routing: {strategy: '<string>', fallback: ['<string>'], allow_upgrade: true},
    cache: {enabled: true, ttl: 123}
  })
};

fetch('https://api.openmodex.com/v1/chat/completions', 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.openmodex.com/v1/chat/completions",
  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([
    'model' => '<string>',
    'messages' => [
        [
                'content' => '<string>',
                'name' => '<string>',
                'tool_call_id' => '<string>',
                'tool_calls' => [
                                [
                                                                'id' => '<string>',
                                                                'type' => 'function',
                                                                'function' => [
                                                                                                                                'name' => '<string>',
                                                                                                                                'arguments' => '<string>'
                                                                ]
                                ]
                ]
        ]
    ],
    'stream' => false,
    'temperature' => 1,
    'top_p' => 123,
    'n' => 123,
    'max_tokens' => 123,
    'stop' => '<string>',
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'logit_bias' => [
        
    ],
    'tools' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => '<string>',
                                'description' => '<string>',
                                'parameters' => [
                                                                
                                ]
                ]
        ]
    ],
    'tool_choice' => '<string>',
    'response_format' => [
        'type' => '<string>'
    ],
    'seed' => 123,
    'user' => '<string>',
    'routing' => [
        'strategy' => '<string>',
        'fallback' => [
                '<string>'
        ],
        'allow_upgrade' => true
    ],
    'cache' => [
        'enabled' => true,
        'ttl' => 123
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($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.openmodex.com/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ]\n    }\n  ],\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"max_tokens\": 123,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"logit_bias\": {},\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {\n    \"type\": \"<string>\"\n  },\n  \"seed\": 123,\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"strategy\": \"<string>\",\n    \"fallback\": [\n      \"<string>\"\n    ],\n    \"allow_upgrade\": true\n  },\n  \"cache\": {\n    \"enabled\": true,\n    \"ttl\": 123\n  }\n}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	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.openmodex.com/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ]\n    }\n  ],\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"max_tokens\": 123,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"logit_bias\": {},\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {\n    \"type\": \"<string>\"\n  },\n  \"seed\": 123,\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"strategy\": \"<string>\",\n    \"fallback\": [\n      \"<string>\"\n    ],\n    \"allow_upgrade\": true\n  },\n  \"cache\": {\n    \"enabled\": true,\n    \"ttl\": 123\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.openmodex.com/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"<string>\",\n      \"tool_calls\": [\n        {\n          \"id\": \"<string>\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"<string>\",\n            \"arguments\": \"<string>\"\n          }\n        }\n      ]\n    }\n  ],\n  \"stream\": false,\n  \"temperature\": 1,\n  \"top_p\": 123,\n  \"n\": 123,\n  \"max_tokens\": 123,\n  \"stop\": \"<string>\",\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"logit_bias\": {},\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"<string>\",\n        \"description\": \"<string>\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"tool_choice\": \"<string>\",\n  \"response_format\": {\n    \"type\": \"<string>\"\n  },\n  \"seed\": 123,\n  \"user\": \"<string>\",\n  \"routing\": {\n    \"strategy\": \"<string>\",\n    \"fallback\": [\n      \"<string>\"\n    ],\n    \"allow_upgrade\": true\n  },\n  \"cache\": {\n    \"enabled\": true,\n    \"ttl\": 123\n  }\n}"

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

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "<string>",
        "content": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "cost_usd": 123
  },
  "system_fingerprint": "<string>",
  "openmodex": {
    "request_id": "<string>",
    "model_used": "<string>",
    "provider": "<string>",
    "cache_hit": true,
    "routing_strategy": "<string>",
    "fallback_used": true,
    "latency_ms": 123
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

Thân Yêu Cầu

string

bắt buộc

ID mô hình để sử dụng (ví dụ: gpt-4o, claude-3.5-sonnet, gemini-2.0-flash).

array

bắt buộc

Danh sách tin nhắn tạo thành cuộc hội thoại.

Hiện Đối tượng Message

string

bắt buộc

Một trong system, user, assistant hoặc tool.

string

bắt buộc

Nội dung của tin nhắn.

string

Tên tùy chọn cho người tham gia.

boolean

mặc định:false

Nếu true, trả về luồng Server-Sent Events (SSE).

number

mặc định:1

Nhiệt độ lấy mẫu từ 0 đến 2. Giá trị thấp hơn cho kết quả xác định hơn.

integer

Số lượng token tối đa để tạo.

number

mặc định:1

Tham số lấy mẫu nucleus.

string | string[]

Chuỗi dừng sẽ ngừng việc tạo.

number

mặc định:0

Hình phạt tần suất token (-2.0 đến 2.0).

number

mặc định:0

Hình phạt sự hiện diện token (-2.0 đến 2.0).

array

Danh sách công cụ mà mô hình có thể gọi (function calling).

string | object

Kiểm soát công cụ nào được gọi. auto, none hoặc một công cụ cụ thể.

object

Buộc định dạng đầu ra cụ thể (ví dụ: {"type": "json_object"}).

integer

Seed lấy mẫu xác định để tái tạo kết quả.

Phần Mở Rộng OpenModex

object

Cấu hình định tuyến thông minh cho yêu cầu này.

Hiện Đối tượng Routing

string

cost_optimized, latency_optimized hoặc quality_optimized.

string[]

Chuỗi mô hình dự phòng phía máy chủ.

boolean

Cho phép định tuyến đến mô hình tốt hơn ở cùng mức giá.

object

Cấu hình bộ nhớ đệm prompt.

Hiện Đối tượng Cache

boolean

Bật bộ nhớ đệm prompt cho yêu cầu này.

integer

Thời gian sống của bộ đệm tính bằng giây.

Phản Hồi

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "gpt-4o-2024-08-06",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 9,
    "total_tokens": 19,
    "cost_usd": 0.000145
  },
  "openmodex": {
    "request_id": "req_abc123",
    "model_used": "gpt-4o-2024-08-06",
    "provider": "openai",
    "cache_hit": false,
    "routing_strategy": "default",
    "fallback_used": false,
    "latency_ms": 850
  }
}

Ví Dụ

curl https://api.openmodex.com/v1/chat/completions \
  -H "Authorization: Bearer omx_sk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7,
    "max_tokens": 100
  }'

import OpenModex from '@openmodex/sdk';

const client = new OpenModex({ apiKey: 'omx_sk_YOUR_KEY' });

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of France?' },
  ],
  temperature: 0.7,
  max_tokens: 100,
});

console.log(response.choices[0].message.content);

from openmodex import OpenModex

client = OpenModex(api_key="omx_sk_YOUR_KEY")

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"},
    ],
    temperature=0.7,
    max_tokens=100,
)

print(response.choices[0].message.content)

Ủy quyền

Authorization

string

header

bắt buộc

API key authentication. Pass your OpenModex API key as a Bearer token in the Authorization header: Authorization: Bearer omx_sk_...

Nội dung

application/json

Request body for creating a chat completion.

model

string

bắt buộc

ID of the model to use.

messages

object[]

bắt buộc

A list of messages comprising the conversation so far.

Show child attributes

stream

boolean

mặc định:false

If true, partial message deltas will be sent as server-sent events.

temperature

number

Sampling temperature between 0 and 2. Higher values make output more random.

Phạm vi bắt buộc: 0 <= x <= 2

top_p

number

Nucleus sampling parameter. Only consider tokens with top_p probability mass.

integer

How many completions to generate for each prompt.

max_tokens

integer

The maximum number of tokens to generate in the completion.

stop

Up to 4 sequences where the API will stop generating further tokens.

frequency_penalty

number

Penalizes new tokens based on their existing frequency in the text so far.

Phạm vi bắt buộc: -2 <= x <= 2

presence_penalty

number

Penalizes new tokens based on whether they appear in the text so far.

Phạm vi bắt buộc: -2 <= x <= 2

logit_bias

object

Modify the likelihood of specified tokens appearing in the completion. Maps token IDs to bias values from -100 to 100.

Show child attributes

tools

object[]

A list of tools the model may call.

Show child attributes

tool_choice

Controls which tool is called by the model. Can be 'none', 'auto', 'required', or a specific tool object.

response_format

object

An object specifying the format the model must output (e.g., {"type": "json_object"}).

Show child attributes

seed

integer

If specified, the system will attempt to sample deterministically.

user

string

A unique identifier representing your end-user, for abuse monitoring.

routing

object

Configuration for intelligent request routing.

Show child attributes

cache

object

Configuration for response caching.

Show child attributes

Phản hồi

Chat completion response. When stream=true, returns SSE stream of ChatCompletionChunk objects.

Response from a chat completion request.

string

A unique identifier for the completion.

object

enum<string>

The object type, always 'chat.completion'.

Tùy chọn có sẵn:

chat.completion

created

integer

Unix timestamp (in seconds) of when the completion was created.

model

string

The model used for the completion.

choices

object[]

A list of completion choices.

Show child attributes

usage

object

Token usage statistics for a completion request.

Show child attributes

system_fingerprint

string

A fingerprint representing the backend configuration.

openmodex

object

OpenModex-specific metadata included in completion responses.

Show child attributes

Tổng quan

Trò chuyện

Hoàn thành

Nhúng

Mô hình

Tạo hoàn thành chat

Thân Yêu Cầu

Phần Mở Rộng OpenModex

Phản Hồi

Ví Dụ

Ủy quyền

Nội dung

Phản hồi

​Thân Yêu Cầu

​Phần Mở Rộng OpenModex

​Phản Hồi

​Ví Dụ

Ủy quyền

Nội dung

Phản hồi

Thân Yêu Cầu

Phần Mở Rộng OpenModex

Phản Hồi

Ví Dụ