Chat Completions

POST /chat/completions

对话完成接口

cURL

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": {
    "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
}
'

200

{
  "id": "<string>",
  "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>"
            }
          }
        ]
      },
      "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>"
}

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

bearerAuthapiKeyAuth

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 · enum<string> 托管工具 · object 函数工具 · object

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

n · 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

200

application/json

成功响应

id · 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