Chat Completions

对话完成接口

curl --request POST \
  --url https://geekai.co/api/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5-mini",
  "messages": [
    {
      "content": "你是一个助手",
      "role": "system"
    },
    {
      "content": "你好",
      "role": "user"
    }
  ],
  "enable_thinking": false,
  "thinking": {
    "type": "adaptive",
    "include_thoughts": false,
    "budget_tokens": 16000,
    "reasoning_effort": "medium",
    "thinking_level": "high"
  },
  "stream": false,
  "background": false,
  "enable_search": false,
  "search_config": {
    "engine": "glm/search-std",
    "prompt": "<string>",
    "intent": false,
    "count": 10,
    "domain_filter": "<string>",
    "recency_filter": "noLimit",
    "content_size": "medium",
    "return_result": false,
    "result_sequence": "after",
    "require_search": false,
    "deepable": false
  },
  "enable_url_context": false,
  "temperature": 123,
  "max_completion_tokens": 4096,
  "json_mode": false,
  "response_format": {
    "type": "text"
  },
  "modalities": [],
  "audio": {
    "voice": "alloy",
    "format": "wav"
  },
  "image": {
    "image_size": "1K"
  },
  "tools": "<array>",
  "tool_config": {
    "functionCallingConfig": {
      "mode": "AUTO",
      "allowedFunctionNames": [
        "<string>"
      ]
    }
  },
  "parallel_tool_calls": true,
  "image_generation": false,
  "stop": [
    "<string>"
  ],
  "logprobs": false,
  "top_logprobs": 2,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "top_p": 1,
  "top_k": 1,
  "seed": 123,
  "n": 1,
  "metadata": {},
  "sess_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retries": 0
}
'

import requests

url = "https://geekai.co/api/v1/chat/completions"

payload = {
    "model": "gpt-5-mini",
    "messages": [
        {
            "content": "你是一个助手",
            "role": "system"
        },
        {
            "content": "你好",
            "role": "user"
        }
    ],
    "enable_thinking": False,
    "thinking": {
        "type": "adaptive",
        "include_thoughts": False,
        "budget_tokens": 16000,
        "reasoning_effort": "medium",
        "thinking_level": "high"
    },
    "stream": False,
    "background": False,
    "enable_search": False,
    "search_config": {
        "engine": "glm/search-std",
        "prompt": "<string>",
        "intent": False,
        "count": 10,
        "domain_filter": "<string>",
        "recency_filter": "noLimit",
        "content_size": "medium",
        "return_result": False,
        "result_sequence": "after",
        "require_search": False,
        "deepable": False
    },
    "enable_url_context": False,
    "temperature": 123,
    "max_completion_tokens": 4096,
    "json_mode": False,
    "response_format": { "type": "text" },
    "modalities": [],
    "audio": {
        "voice": "alloy",
        "format": "wav"
    },
    "image": { "image_size": "1K" },
    "tools": "<array>",
    "tool_config": { "functionCallingConfig": {
            "mode": "AUTO",
            "allowedFunctionNames": ["<string>"]
        } },
    "parallel_tool_calls": True,
    "image_generation": False,
    "stop": ["<string>"],
    "logprobs": False,
    "top_logprobs": 2,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "top_p": 1,
    "top_k": 1,
    "seed": 123,
    "n": 1,
    "metadata": {},
    "sess_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "retries": 0
}
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: 'gpt-5-mini',
    messages: [{content: '你是一个助手', role: 'system'}, {content: '你好', role: 'user'}],
    enable_thinking: false,
    thinking: {
      type: 'adaptive',
      include_thoughts: false,
      budget_tokens: 16000,
      reasoning_effort: 'medium',
      thinking_level: 'high'
    },
    stream: false,
    background: false,
    enable_search: false,
    search_config: {
      engine: 'glm/search-std',
      prompt: '<string>',
      intent: false,
      count: 10,
      domain_filter: '<string>',
      recency_filter: 'noLimit',
      content_size: 'medium',
      return_result: false,
      result_sequence: 'after',
      require_search: false,
      deepable: false
    },
    enable_url_context: false,
    temperature: 123,
    max_completion_tokens: 4096,
    json_mode: false,
    response_format: {type: 'text'},
    modalities: [],
    audio: {voice: 'alloy', format: 'wav'},
    image: {image_size: '1K'},
    tools: '<array>',
    tool_config: {functionCallingConfig: {mode: 'AUTO', allowedFunctionNames: ['<string>']}},
    parallel_tool_calls: true,
    image_generation: false,
    stop: ['<string>'],
    logprobs: false,
    top_logprobs: 2,
    frequency_penalty: 0,
    presence_penalty: 0,
    top_p: 1,
    top_k: 1,
    seed: 123,
    n: 1,
    metadata: {},
    sess_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    retries: 0
  })
};

fetch('https://geekai.co/api/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://geekai.co/api/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' => 'gpt-5-mini',
    'messages' => [
        [
                'content' => '你是一个助手',
                'role' => 'system'
        ],
        [
                'content' => '你好',
                'role' => 'user'
        ]
    ],
    'enable_thinking' => false,
    'thinking' => [
        'type' => 'adaptive',
        'include_thoughts' => false,
        'budget_tokens' => 16000,
        'reasoning_effort' => 'medium',
        'thinking_level' => 'high'
    ],
    'stream' => false,
    'background' => false,
    'enable_search' => false,
    'search_config' => [
        'engine' => 'glm/search-std',
        'prompt' => '<string>',
        'intent' => false,
        'count' => 10,
        'domain_filter' => '<string>',
        'recency_filter' => 'noLimit',
        'content_size' => 'medium',
        'return_result' => false,
        'result_sequence' => 'after',
        'require_search' => false,
        'deepable' => false
    ],
    'enable_url_context' => false,
    'temperature' => 123,
    'max_completion_tokens' => 4096,
    'json_mode' => false,
    'response_format' => [
        'type' => 'text'
    ],
    'modalities' => [
        
    ],
    'audio' => [
        'voice' => 'alloy',
        'format' => 'wav'
    ],
    'image' => [
        'image_size' => '1K'
    ],
    'tools' => '<array>',
    'tool_config' => [
        'functionCallingConfig' => [
                'mode' => 'AUTO',
                'allowedFunctionNames' => [
                                '<string>'
                ]
        ]
    ],
    'parallel_tool_calls' => true,
    'image_generation' => false,
    'stop' => [
        '<string>'
    ],
    'logprobs' => false,
    'top_logprobs' => 2,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'top_p' => 1,
    'top_k' => 1,
    'seed' => 123,
    'n' => 1,
    'metadata' => [
        
    ],
    'sess_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    'retries' => 0
  ]),
  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://geekai.co/api/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gpt-5-mini\",\n  \"messages\": [\n    {\n      \"content\": \"你是一个助手\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"你好\",\n      \"role\": \"user\"\n    }\n  ],\n  \"enable_thinking\": false,\n  \"thinking\": {\n    \"type\": \"adaptive\",\n    \"include_thoughts\": false,\n    \"budget_tokens\": 16000,\n    \"reasoning_effort\": \"medium\",\n    \"thinking_level\": \"high\"\n  },\n  \"stream\": false,\n  \"background\": false,\n  \"enable_search\": false,\n  \"search_config\": {\n    \"engine\": \"glm/search-std\",\n    \"prompt\": \"<string>\",\n    \"intent\": false,\n    \"count\": 10,\n    \"domain_filter\": \"<string>\",\n    \"recency_filter\": \"noLimit\",\n    \"content_size\": \"medium\",\n    \"return_result\": false,\n    \"result_sequence\": \"after\",\n    \"require_search\": false,\n    \"deepable\": false\n  },\n  \"enable_url_context\": false,\n  \"temperature\": 123,\n  \"max_completion_tokens\": 4096,\n  \"json_mode\": false,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"modalities\": [],\n  \"audio\": {\n    \"voice\": \"alloy\",\n    \"format\": \"wav\"\n  },\n  \"image\": {\n    \"image_size\": \"1K\"\n  },\n  \"tools\": \"<array>\",\n  \"tool_config\": {\n    \"functionCallingConfig\": {\n      \"mode\": \"AUTO\",\n      \"allowedFunctionNames\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"parallel_tool_calls\": true,\n  \"image_generation\": false,\n  \"stop\": [\n    \"<string>\"\n  ],\n  \"logprobs\": false,\n  \"top_logprobs\": 2,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"top_p\": 1,\n  \"top_k\": 1,\n  \"seed\": 123,\n  \"n\": 1,\n  \"metadata\": {},\n  \"sess_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"retries\": 0\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://geekai.co/api/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-5-mini\",\n  \"messages\": [\n    {\n      \"content\": \"你是一个助手\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"你好\",\n      \"role\": \"user\"\n    }\n  ],\n  \"enable_thinking\": false,\n  \"thinking\": {\n    \"type\": \"adaptive\",\n    \"include_thoughts\": false,\n    \"budget_tokens\": 16000,\n    \"reasoning_effort\": \"medium\",\n    \"thinking_level\": \"high\"\n  },\n  \"stream\": false,\n  \"background\": false,\n  \"enable_search\": false,\n  \"search_config\": {\n    \"engine\": \"glm/search-std\",\n    \"prompt\": \"<string>\",\n    \"intent\": false,\n    \"count\": 10,\n    \"domain_filter\": \"<string>\",\n    \"recency_filter\": \"noLimit\",\n    \"content_size\": \"medium\",\n    \"return_result\": false,\n    \"result_sequence\": \"after\",\n    \"require_search\": false,\n    \"deepable\": false\n  },\n  \"enable_url_context\": false,\n  \"temperature\": 123,\n  \"max_completion_tokens\": 4096,\n  \"json_mode\": false,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"modalities\": [],\n  \"audio\": {\n    \"voice\": \"alloy\",\n    \"format\": \"wav\"\n  },\n  \"image\": {\n    \"image_size\": \"1K\"\n  },\n  \"tools\": \"<array>\",\n  \"tool_config\": {\n    \"functionCallingConfig\": {\n      \"mode\": \"AUTO\",\n      \"allowedFunctionNames\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"parallel_tool_calls\": true,\n  \"image_generation\": false,\n  \"stop\": [\n    \"<string>\"\n  ],\n  \"logprobs\": false,\n  \"top_logprobs\": 2,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"top_p\": 1,\n  \"top_k\": 1,\n  \"seed\": 123,\n  \"n\": 1,\n  \"metadata\": {},\n  \"sess_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"retries\": 0\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://geekai.co/api/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\": \"gpt-5-mini\",\n  \"messages\": [\n    {\n      \"content\": \"你是一个助手\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"你好\",\n      \"role\": \"user\"\n    }\n  ],\n  \"enable_thinking\": false,\n  \"thinking\": {\n    \"type\": \"adaptive\",\n    \"include_thoughts\": false,\n    \"budget_tokens\": 16000,\n    \"reasoning_effort\": \"medium\",\n    \"thinking_level\": \"high\"\n  },\n  \"stream\": false,\n  \"background\": false,\n  \"enable_search\": false,\n  \"search_config\": {\n    \"engine\": \"glm/search-std\",\n    \"prompt\": \"<string>\",\n    \"intent\": false,\n    \"count\": 10,\n    \"domain_filter\": \"<string>\",\n    \"recency_filter\": \"noLimit\",\n    \"content_size\": \"medium\",\n    \"return_result\": false,\n    \"result_sequence\": \"after\",\n    \"require_search\": false,\n    \"deepable\": false\n  },\n  \"enable_url_context\": false,\n  \"temperature\": 123,\n  \"max_completion_tokens\": 4096,\n  \"json_mode\": false,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"modalities\": [],\n  \"audio\": {\n    \"voice\": \"alloy\",\n    \"format\": \"wav\"\n  },\n  \"image\": {\n    \"image_size\": \"1K\"\n  },\n  \"tools\": \"<array>\",\n  \"tool_config\": {\n    \"functionCallingConfig\": {\n      \"mode\": \"AUTO\",\n      \"allowedFunctionNames\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"parallel_tool_calls\": true,\n  \"image_generation\": false,\n  \"stop\": [\n    \"<string>\"\n  ],\n  \"logprobs\": false,\n  \"top_logprobs\": 2,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"top_p\": 1,\n  \"top_k\": 1,\n  \"seed\": 123,\n  \"n\": 1,\n  \"metadata\": {},\n  \"sess_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"retries\": 0\n}"

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

{
  "id": "<string>",
  "status": "pending",
  "created": 123,
  "model": "<string>",
  "object": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "reasoning_content": "<string>",
        "image": "<string>",
        "audio": {
          "id": "<string>",
          "data": "<string>",
          "expires_at": 123,
          "transcript": "<string>"
        },
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop",
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ],
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ]
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "billed_units": 123,
    "prompt_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "cached_tokens": 123,
      "image_tokens": 123,
      "video_tokens": 123,
      "citation_tokens": 123
    },
    "completion_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123
    }
  },
  "citations": [
    "<string>"
  ],
  "system_fingerprint": "<string>"
}

{
  "code": "validation_error",
  "message": "参数验证失败",
  "details": {
    "field": "错误描述"
  }
}

{
  "code": "unauthorized",
  "message": "Invalid API key or token"
}

{
  "code": "invalid_request",
  "message": "请求参数不合法"
}

POST

chat

completions

对话完成接口

curl --request POST \
  --url https://geekai.co/api/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-5-mini",
  "messages": [
    {
      "content": "你是一个助手",
      "role": "system"
    },
    {
      "content": "你好",
      "role": "user"
    }
  ],
  "enable_thinking": false,
  "thinking": {
    "type": "adaptive",
    "include_thoughts": false,
    "budget_tokens": 16000,
    "reasoning_effort": "medium",
    "thinking_level": "high"
  },
  "stream": false,
  "background": false,
  "enable_search": false,
  "search_config": {
    "engine": "glm/search-std",
    "prompt": "<string>",
    "intent": false,
    "count": 10,
    "domain_filter": "<string>",
    "recency_filter": "noLimit",
    "content_size": "medium",
    "return_result": false,
    "result_sequence": "after",
    "require_search": false,
    "deepable": false
  },
  "enable_url_context": false,
  "temperature": 123,
  "max_completion_tokens": 4096,
  "json_mode": false,
  "response_format": {
    "type": "text"
  },
  "modalities": [],
  "audio": {
    "voice": "alloy",
    "format": "wav"
  },
  "image": {
    "image_size": "1K"
  },
  "tools": "<array>",
  "tool_config": {
    "functionCallingConfig": {
      "mode": "AUTO",
      "allowedFunctionNames": [
        "<string>"
      ]
    }
  },
  "parallel_tool_calls": true,
  "image_generation": false,
  "stop": [
    "<string>"
  ],
  "logprobs": false,
  "top_logprobs": 2,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "top_p": 1,
  "top_k": 1,
  "seed": 123,
  "n": 1,
  "metadata": {},
  "sess_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retries": 0
}
'

import requests

url = "https://geekai.co/api/v1/chat/completions"

payload = {
    "model": "gpt-5-mini",
    "messages": [
        {
            "content": "你是一个助手",
            "role": "system"
        },
        {
            "content": "你好",
            "role": "user"
        }
    ],
    "enable_thinking": False,
    "thinking": {
        "type": "adaptive",
        "include_thoughts": False,
        "budget_tokens": 16000,
        "reasoning_effort": "medium",
        "thinking_level": "high"
    },
    "stream": False,
    "background": False,
    "enable_search": False,
    "search_config": {
        "engine": "glm/search-std",
        "prompt": "<string>",
        "intent": False,
        "count": 10,
        "domain_filter": "<string>",
        "recency_filter": "noLimit",
        "content_size": "medium",
        "return_result": False,
        "result_sequence": "after",
        "require_search": False,
        "deepable": False
    },
    "enable_url_context": False,
    "temperature": 123,
    "max_completion_tokens": 4096,
    "json_mode": False,
    "response_format": { "type": "text" },
    "modalities": [],
    "audio": {
        "voice": "alloy",
        "format": "wav"
    },
    "image": { "image_size": "1K" },
    "tools": "<array>",
    "tool_config": { "functionCallingConfig": {
            "mode": "AUTO",
            "allowedFunctionNames": ["<string>"]
        } },
    "parallel_tool_calls": True,
    "image_generation": False,
    "stop": ["<string>"],
    "logprobs": False,
    "top_logprobs": 2,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "top_p": 1,
    "top_k": 1,
    "seed": 123,
    "n": 1,
    "metadata": {},
    "sess_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "retries": 0
}
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: 'gpt-5-mini',
    messages: [{content: '你是一个助手', role: 'system'}, {content: '你好', role: 'user'}],
    enable_thinking: false,
    thinking: {
      type: 'adaptive',
      include_thoughts: false,
      budget_tokens: 16000,
      reasoning_effort: 'medium',
      thinking_level: 'high'
    },
    stream: false,
    background: false,
    enable_search: false,
    search_config: {
      engine: 'glm/search-std',
      prompt: '<string>',
      intent: false,
      count: 10,
      domain_filter: '<string>',
      recency_filter: 'noLimit',
      content_size: 'medium',
      return_result: false,
      result_sequence: 'after',
      require_search: false,
      deepable: false
    },
    enable_url_context: false,
    temperature: 123,
    max_completion_tokens: 4096,
    json_mode: false,
    response_format: {type: 'text'},
    modalities: [],
    audio: {voice: 'alloy', format: 'wav'},
    image: {image_size: '1K'},
    tools: '<array>',
    tool_config: {functionCallingConfig: {mode: 'AUTO', allowedFunctionNames: ['<string>']}},
    parallel_tool_calls: true,
    image_generation: false,
    stop: ['<string>'],
    logprobs: false,
    top_logprobs: 2,
    frequency_penalty: 0,
    presence_penalty: 0,
    top_p: 1,
    top_k: 1,
    seed: 123,
    n: 1,
    metadata: {},
    sess_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    retries: 0
  })
};

fetch('https://geekai.co/api/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://geekai.co/api/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' => 'gpt-5-mini',
    'messages' => [
        [
                'content' => '你是一个助手',
                'role' => 'system'
        ],
        [
                'content' => '你好',
                'role' => 'user'
        ]
    ],
    'enable_thinking' => false,
    'thinking' => [
        'type' => 'adaptive',
        'include_thoughts' => false,
        'budget_tokens' => 16000,
        'reasoning_effort' => 'medium',
        'thinking_level' => 'high'
    ],
    'stream' => false,
    'background' => false,
    'enable_search' => false,
    'search_config' => [
        'engine' => 'glm/search-std',
        'prompt' => '<string>',
        'intent' => false,
        'count' => 10,
        'domain_filter' => '<string>',
        'recency_filter' => 'noLimit',
        'content_size' => 'medium',
        'return_result' => false,
        'result_sequence' => 'after',
        'require_search' => false,
        'deepable' => false
    ],
    'enable_url_context' => false,
    'temperature' => 123,
    'max_completion_tokens' => 4096,
    'json_mode' => false,
    'response_format' => [
        'type' => 'text'
    ],
    'modalities' => [
        
    ],
    'audio' => [
        'voice' => 'alloy',
        'format' => 'wav'
    ],
    'image' => [
        'image_size' => '1K'
    ],
    'tools' => '<array>',
    'tool_config' => [
        'functionCallingConfig' => [
                'mode' => 'AUTO',
                'allowedFunctionNames' => [
                                '<string>'
                ]
        ]
    ],
    'parallel_tool_calls' => true,
    'image_generation' => false,
    'stop' => [
        '<string>'
    ],
    'logprobs' => false,
    'top_logprobs' => 2,
    'frequency_penalty' => 0,
    'presence_penalty' => 0,
    'top_p' => 1,
    'top_k' => 1,
    'seed' => 123,
    'n' => 1,
    'metadata' => [
        
    ],
    'sess_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a',
    'retries' => 0
  ]),
  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://geekai.co/api/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gpt-5-mini\",\n  \"messages\": [\n    {\n      \"content\": \"你是一个助手\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"你好\",\n      \"role\": \"user\"\n    }\n  ],\n  \"enable_thinking\": false,\n  \"thinking\": {\n    \"type\": \"adaptive\",\n    \"include_thoughts\": false,\n    \"budget_tokens\": 16000,\n    \"reasoning_effort\": \"medium\",\n    \"thinking_level\": \"high\"\n  },\n  \"stream\": false,\n  \"background\": false,\n  \"enable_search\": false,\n  \"search_config\": {\n    \"engine\": \"glm/search-std\",\n    \"prompt\": \"<string>\",\n    \"intent\": false,\n    \"count\": 10,\n    \"domain_filter\": \"<string>\",\n    \"recency_filter\": \"noLimit\",\n    \"content_size\": \"medium\",\n    \"return_result\": false,\n    \"result_sequence\": \"after\",\n    \"require_search\": false,\n    \"deepable\": false\n  },\n  \"enable_url_context\": false,\n  \"temperature\": 123,\n  \"max_completion_tokens\": 4096,\n  \"json_mode\": false,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"modalities\": [],\n  \"audio\": {\n    \"voice\": \"alloy\",\n    \"format\": \"wav\"\n  },\n  \"image\": {\n    \"image_size\": \"1K\"\n  },\n  \"tools\": \"<array>\",\n  \"tool_config\": {\n    \"functionCallingConfig\": {\n      \"mode\": \"AUTO\",\n      \"allowedFunctionNames\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"parallel_tool_calls\": true,\n  \"image_generation\": false,\n  \"stop\": [\n    \"<string>\"\n  ],\n  \"logprobs\": false,\n  \"top_logprobs\": 2,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"top_p\": 1,\n  \"top_k\": 1,\n  \"seed\": 123,\n  \"n\": 1,\n  \"metadata\": {},\n  \"sess_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"retries\": 0\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://geekai.co/api/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-5-mini\",\n  \"messages\": [\n    {\n      \"content\": \"你是一个助手\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"你好\",\n      \"role\": \"user\"\n    }\n  ],\n  \"enable_thinking\": false,\n  \"thinking\": {\n    \"type\": \"adaptive\",\n    \"include_thoughts\": false,\n    \"budget_tokens\": 16000,\n    \"reasoning_effort\": \"medium\",\n    \"thinking_level\": \"high\"\n  },\n  \"stream\": false,\n  \"background\": false,\n  \"enable_search\": false,\n  \"search_config\": {\n    \"engine\": \"glm/search-std\",\n    \"prompt\": \"<string>\",\n    \"intent\": false,\n    \"count\": 10,\n    \"domain_filter\": \"<string>\",\n    \"recency_filter\": \"noLimit\",\n    \"content_size\": \"medium\",\n    \"return_result\": false,\n    \"result_sequence\": \"after\",\n    \"require_search\": false,\n    \"deepable\": false\n  },\n  \"enable_url_context\": false,\n  \"temperature\": 123,\n  \"max_completion_tokens\": 4096,\n  \"json_mode\": false,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"modalities\": [],\n  \"audio\": {\n    \"voice\": \"alloy\",\n    \"format\": \"wav\"\n  },\n  \"image\": {\n    \"image_size\": \"1K\"\n  },\n  \"tools\": \"<array>\",\n  \"tool_config\": {\n    \"functionCallingConfig\": {\n      \"mode\": \"AUTO\",\n      \"allowedFunctionNames\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"parallel_tool_calls\": true,\n  \"image_generation\": false,\n  \"stop\": [\n    \"<string>\"\n  ],\n  \"logprobs\": false,\n  \"top_logprobs\": 2,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"top_p\": 1,\n  \"top_k\": 1,\n  \"seed\": 123,\n  \"n\": 1,\n  \"metadata\": {},\n  \"sess_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"retries\": 0\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://geekai.co/api/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\": \"gpt-5-mini\",\n  \"messages\": [\n    {\n      \"content\": \"你是一个助手\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"你好\",\n      \"role\": \"user\"\n    }\n  ],\n  \"enable_thinking\": false,\n  \"thinking\": {\n    \"type\": \"adaptive\",\n    \"include_thoughts\": false,\n    \"budget_tokens\": 16000,\n    \"reasoning_effort\": \"medium\",\n    \"thinking_level\": \"high\"\n  },\n  \"stream\": false,\n  \"background\": false,\n  \"enable_search\": false,\n  \"search_config\": {\n    \"engine\": \"glm/search-std\",\n    \"prompt\": \"<string>\",\n    \"intent\": false,\n    \"count\": 10,\n    \"domain_filter\": \"<string>\",\n    \"recency_filter\": \"noLimit\",\n    \"content_size\": \"medium\",\n    \"return_result\": false,\n    \"result_sequence\": \"after\",\n    \"require_search\": false,\n    \"deepable\": false\n  },\n  \"enable_url_context\": false,\n  \"temperature\": 123,\n  \"max_completion_tokens\": 4096,\n  \"json_mode\": false,\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"modalities\": [],\n  \"audio\": {\n    \"voice\": \"alloy\",\n    \"format\": \"wav\"\n  },\n  \"image\": {\n    \"image_size\": \"1K\"\n  },\n  \"tools\": \"<array>\",\n  \"tool_config\": {\n    \"functionCallingConfig\": {\n      \"mode\": \"AUTO\",\n      \"allowedFunctionNames\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"parallel_tool_calls\": true,\n  \"image_generation\": false,\n  \"stop\": [\n    \"<string>\"\n  ],\n  \"logprobs\": false,\n  \"top_logprobs\": 2,\n  \"frequency_penalty\": 0,\n  \"presence_penalty\": 0,\n  \"top_p\": 1,\n  \"top_k\": 1,\n  \"seed\": 123,\n  \"n\": 1,\n  \"metadata\": {},\n  \"sess_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\",\n  \"retries\": 0\n}"

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

{
  "id": "<string>",
  "status": "pending",
  "created": 123,
  "model": "<string>",
  "object": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "reasoning_content": "<string>",
        "image": "<string>",
        "audio": {
          "id": "<string>",
          "data": "<string>",
          "expires_at": 123,
          "transcript": "<string>"
        },
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop",
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ],
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ]
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "billed_units": 123,
    "prompt_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "cached_tokens": 123,
      "image_tokens": 123,
      "video_tokens": 123,
      "citation_tokens": 123
    },
    "completion_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "accepted_prediction_tokens": 123,
      "rejected_prediction_tokens": 123
    }
  },
  "citations": [
    "<string>"
  ],
  "system_fingerprint": "<string>"
}

{
  "code": "validation_error",
  "message": "参数验证失败",
  "details": {
    "field": "错误描述"
  }
}

{
  "code": "unauthorized",
  "message": "Invalid API key or token"
}

{
  "code": "invalid_request",
  "message": "请求参数不合法"
}

Note: For setting the chat model name, refer to System Supported Chat Model List. The request/response parameter structure is fully compatible with OpenAI. When switching models, you only need to modify the corresponding model name. If the model request/response parameters are inconsistent with OpenAI, GeekAI will automatically convert and align them. Except for Baidu ERNIE Bot and iFlytek Spark, all other platforms support function calling (the specific supported models are subject to platform restrictions). When calling the GPTs model API, you need to replace the * in gpt-4-gizmo-* with the corresponding GPTs’ gizmo_id, which can be obtained by extracting it from the GPTs URL. For example, for https://chatgpt.com/g/g-bo0FiWLY7-researchgpt, the corresponding gizmo_id is g-bo0FiWLY7.

The response data structure is fully compatible with OpenAI and builds upon it to add new features for adapting to other models. It provides support for cited links (citations), search billing units (billed_units), video in message content, image/video input tokens, and inference mode settings (thinking). The response structure changes depending on whether it is a streaming output or not. You can refer to the request examples below to make a judgment:

cURL Request Example

curl --location --request POST 'https://geekai.dev/api/v1/chat/completions' \
--header 'Authorization: Bearer {YOUR_GEEKAI_API_KEY}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "gpt-4o-mini",
    "messages": [
        {
            "role": "user",
            "content": "hi"
        }
    ],
    "stream": false
}'

Authorizations

Authorization

string

header

required

API认证token

Body

application/json

model

string

default:gpt-5-mini

required

对话模型

messages

object[]

required

消息列表

Show child attributes

Example:

[
  { "content": "你是一个助手", "role": "system" },
  { "content": "你好", "role": "user" }
]

enable_thinking

boolean

default:false

开启推理模式，仅支持切换思考模式的模型支持

thinking

object

推理模式细节配置

Show child attributes

stream

boolean

default:false

是否返回流式响应，默认false

background

boolean

default:false

是否开启后台任务模式，默认false，注意 stream 和 background 不能同时为 true

enable_search

boolean

default:false

是否启用联网搜索，默认false

search_config

object

联网搜索配置明细，仅智谱清言和不支持内置搜索工具的模型适用

Show child attributes

enable_url_context

boolean

default:false

是否启用 URL Context，默认false，仅部分 Gemini 模型生效

temperature

number

温度参数，默认为代理模型默认值

max_completion_tokens

integer

最大输出token数,默认设置为当前模型最大支持输出

Example:

4096

json_mode

boolean

default:false

是否设置响应格式为JSON对象，默认false

response_format

Text · object

指定响应输出格式，默认不指定为文本输出，如果设置该配置项会覆盖json_mode设置

Text
JSON object
JSON schema

Show child attributes

modalities

enum<string>[]

输出的多模态类型列表

Available options:

text,

image,

audio,

video

audio

object

音频输出配置

Show child attributes

image

object

图像生成配置，仅 Gemini 3 Pro Image 适用

Show child attributes

tools

array

可调用的工具函数列表

tool_choice

模型在生成响应时应如何选择使用哪个工具（或多个工具）

Available options:

none,

auto,

required

tool_config

object

工具函数调用配置(兼容gemini)

Show child attributes

parallel_tool_calls

boolean

default:true

是否并发调用工具函数

image_generation

boolean

default:false

是否强制出图，仅支持对话画图的模型支持

stop

string[]

停止生成的触发词列表

logprobs

boolean

default:false

是否返回token概率

top_logprobs

integer

每个位置返回的最可能token数

Example:

2

frequency_penalty

number

default:0

频率惩罚系数

presence_penalty

number

default:0

存在惩罚系数

top_p

number

default:1

核采样阈值

top_k

integer

default:1

最高概率采样数

seed

integer

随机数种子

integer

default:1

生成结果数量

metadata

object

自定义元数据

sess_id

string<uuid>

第三方应用自行实现的会话ID

retries

integer

default:0

自动重试次数，默认0

Response

成功响应

string

请求ID

status

enum<string>

请求状态，只有后台模式才会返回

Available options:

pending,

running,

succeed

created

integer

请求创建Unix时间戳

model

string

对话使用的模型

object

string

响应对象类型

choices

object[]

生成的对话列表

Show child attributes

usage

object

tokens消耗统计

Show child attributes

citations

string[]

引用的文献/链接列表

system_fingerprint

string

系统指纹

Chat

Image

Audio

Video

Models

Agent

File

OCR

API KEY

cURL Request Example

Authorizations

Body

Response

​cURL Request Example

Authorizations

Body

Response

cURL Request Example