Skip to main content
POST
/
v1
/
chat
/
completions
对话补全
curl --request POST \
  --url https://ai.alad.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "deepseek-v3-2-speciale",
  "messages": [
    {
      "role": "user",
      "content": "你好！"
    }
  ],
  "max_tokens": 8192,
  "temperature": 1,
  "top_p": 0.5,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "stream": false,
  "stop": "<string>"
}
'
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 123,
  "model": "deepseek-v3-2-speciale",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "你好！这里是 DeepSeek V3.2 Speciale，有什么可以帮你的？"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
enum<string>
required

模型 ID

Available options:
deepseek-v3-2-speciale
Example:

"deepseek-v3-2-speciale"

​
messages
object[]
required

对话消息列表。

Minimum array length: 1
Example:
[{ "role": "user", "content": "你好！" }]
​
max_tokens
integer
default:8192

最大生成 Token 数。

Required range: 1 <= x <= 8192
​
temperature
number
default:1

采样温度，值越高输出越随机。

Required range: 0 <= x <= 2
Example:

1

​
top_p
number

核采样阈值。

Required range: 0 <= x <= 1
​
frequency_penalty
number
default:0

根据词频惩罚重复 Token。

Required range: -2 <= x <= 2
​
presence_penalty
number
default:0

惩罚已出现过的 Token。

Required range: -2 <= x <= 2
​
stream
boolean
default:false

为 true 时通过 SSE 流式返回结果。

​
stop

触发停止生成的序列。

Response

成功生成响应

​
id
string
required
Example:

"chatcmpl-abc123"

​
object
string
required
Example:

"chat.completion"

​
created
integer
required

Unix 时间戳

​
model
string
required
Example:

"deepseek-v3-2-speciale"

​
choices
object[]
required
​
usage
object