跳转到主要内容
POST
/
v1
/
chat
/
completions
curl --request POST \
  --url 'https://api.elkapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-5.5",
  "messages": [
    {
      "role": "user",
      "content": "你好，请介绍一下你自己"
    }
  ],
  "temperature": 1,
  "stream": false,
  "max_tokens": 1024,
  "response_format": "json"
}'

{
  "id": "id",
  "object": "chat.completion",
  "created": 1,
  "model": "gpt-5.5",
  "choices": [
    {
      "index": 1,
      "message": {
        "role": "user",
        "content": "你好，请介绍一下你自己",
        "name": "name",
        "tool_calls": [
          {
            "id": {},
            "type": {},
            "function": {}
          }
        ],
        "tool_call_id": "tool_call_id",
        "reasoning_content": "reasoning_content"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1,
    "prompt_tokens_details": {
      "cached_tokens": 1,
      "text_tokens": 1,
      "audio_tokens": 1,
      "image_tokens": 1
    },
    "completion_tokens_details": {
      "text_tokens": 1,
      "audio_tokens": 1,
      "reasoning_tokens": 1
    }
  },
  "system_fingerprint": "system_fingerprint"
}

Documentation Index

Fetch the complete documentation index at: https://docs.elkapi.com/llms.txt

Use this file to discover all available pages before exploring further.

curl --request POST \
  --url 'https://api.elkapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-5.5",
  "messages": [
    {
      "role": "user",
      "content": "你好，请介绍一下你自己"
    }
  ],
  "temperature": 1,
  "stream": false,
  "max_tokens": 1024,
  "response_format": "json"
}'

{
  "id": "id",
  "object": "chat.completion",
  "created": 1,
  "model": "gpt-5.5",
  "choices": [
    {
      "index": 1,
      "message": {
        "role": "user",
        "content": "你好，请介绍一下你自己",
        "name": "name",
        "tool_calls": [
          {
            "id": {},
            "type": {},
            "function": {}
          }
        ],
        "tool_call_id": "tool_call_id",
        "reasoning_content": "reasoning_content"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1,
    "completion_tokens": 1,
    "total_tokens": 1,
    "prompt_tokens_details": {
      "cached_tokens": 1,
      "text_tokens": 1,
      "audio_tokens": 1,
      "image_tokens": 1
    },
    "completion_tokens_details": {
      "text_tokens": 1,
      "audio_tokens": 1,
      "reasoning_tokens": 1
    }
  },
  "system_fingerprint": "system_fingerprint"
}

​
Authorizations

​
Authorization
string
必填
所有接口均需要使用 Bearer Token 进行认证。在请求头中添加：
Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
默认值:"gpt-5.5"
必填
模型 ID示例：gpt-5.5
​
messages
array<object>
必填
对话消息列表
​
messages.role
string
必填
消息角色可选值：system、user、assistant、tool、developer
​
messages.content
string or array<object>
必填
消息内容
​
messages.name
string
发送者名称
​
messages.tool_calls
array<object>
​
messages.tool_calls.id
string
​
messages.tool_calls.type
string
示例：function
​
messages.tool_calls.function
object
​
messages.tool_calls.function.name
string
​
messages.tool_calls.function.arguments
string
​
messages.tool_call_id
string
工具调用 ID（用于 tool 角色消息）
​
messages.reasoning_content
string
推理内容
​
temperature
number
默认值:"1"
采样温度
​
top_p
number
默认值:"1"
核采样参数
​
n
integer
默认值:"1"
生成数量
​
stream
boolean
默认值:"false"
是否流式响应
​
stream_options
object
​
stream_options.include_usage
boolean
​
stop
string or array<string>
停止序列
​
max_tokens
integer
最大生成 Token 数
​
max_completion_tokens
integer
最大补全 Token 数
​
presence_penalty
number
默认值:"0"
​
frequency_penalty
number
默认值:"0"
​
logit_bias
object
​
user
string
​
tools
array<object>
​
tools.type
string
示例：function
​
tools.function
object
​
tools.function.name
string
​
tools.function.description
string
​
tools.function.parameters
object
JSON Schema 格式的参数定义
​
tool_choice
string or object
​
tool_choice.type
string
​
tool_choice.function
object
​
tool_choice.function.name
string
​
response_format
object
​
response_format.type
string
可选值：text、json_object、json_schema
​
response_format.json_schema
object
JSON Schema 定义
​
seed
integer
​
reasoning_effort
string
推理强度 (用于支持推理的模型)可选值：low、medium、high
​
modalities
array<string>
​
audio
object
​
audio.voice
string
​
audio.format
string

​
Response

​
id
string
​
object
string
示例：chat.completion
​
created
integer
​
model
string
默认值:"gpt-5.5"
示例：gpt-5.5
​
choices
array<object>
​
choices.index
integer
​
choices.message
object
​
choices.message.role
string
必填
消息角色可选值：system、user、assistant、tool、developer
​
choices.message.content
string or array<object>
必填
消息内容
​
choices.message.name
string
发送者名称
​
choices.message.tool_calls
array<object>
​
choices.message.tool_calls.id
string
​
choices.message.tool_calls.type
string
示例：function
​
choices.message.tool_calls.function
object
​
choices.message.tool_call_id
string
工具调用 ID（用于 tool 角色消息）
​
choices.message.reasoning_content
string
推理内容
​
choices.finish_reason
string
可选值：stop、length、tool_calls、content_filter
​
usage
object
​
usage.prompt_tokens
integer
提示词 Token 数
​
usage.completion_tokens
integer
补全 Token 数
​
usage.total_tokens
integer
总 Token 数
​
usage.prompt_tokens_details
object
​
usage.prompt_tokens_details.cached_tokens
integer
​
usage.prompt_tokens_details.text_tokens
integer
​
usage.prompt_tokens_details.audio_tokens
integer
​
usage.prompt_tokens_details.image_tokens
integer
​
usage.completion_tokens_details
object
​
usage.completion_tokens_details.text_tokens
integer
​
usage.completion_tokens_details.audio_tokens
integer
​
usage.completion_tokens_details.reasoning_tokens
integer
​
system_fingerprint
string