Vai al contenuto principale
POST
/
kimi
/
chat
/
completions
Kimi Chat Completions
curl --request POST \
  --url https://api.acedata.cloud/kimi/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kimi-k2.5",
  "messages": [
    {
      "role": "user",
      "content": "<string>"
    }
  ],
  "n": 1,
  "stream": false,
  "max_tokens": 123,
  "temperature": 1,
  "response_format": {
    "type": "json_object"
  }
}
'
{
  "id": "<string>",
  "model": "<string>",
  "object": "chat.completion",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>"
      },
      "finish_reason": "stop"
    }
  ],
  "created": 123,
  "system_fingerprint": "<string>"
}

Autorizzazioni

​
Authorization
string
header
obbligatorio

API token from https://platform.acedata.cloud

Intestazioni

​
accept
enum<string>

Specifies the format of the response from the server.

Opzioni disponibili:
application/json

Corpo

application/json
​
model
enum<string>
obbligatorio

ID of the model to use.

Opzioni disponibili:
kimi-k2-thinking-turbo,
kimi-k2.5,
kimi-k2-thinking,
kimi-k2-instruct-0905,
kimi-k2-0905-preview,
kimi-k2-turbo-preview,
kimi-k2-0711-preview
Esempio:

"kimi-k2.5"

​
messages
object[]
obbligatorio

A list of messages comprising the conversation so far.

Minimum array length: 1
​
n
number | null
predefinito:1

How many chat completion choices to generate for each input message.

Intervallo richiesto: 1 <= x <= 128
Esempio:

1

​
stream
boolean | null
predefinito:false

If set, partial message deltas will be sent, like in ChatGPT.

​
max_tokens
number | null

The maximum number of tokens that can be generated in the chat completion.

​
temperature
number | null
predefinito:1

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

Intervallo richiesto: 0 <= x <= 2
Esempio:

1

​
response_format
object

An object specifying the format that the model must output. If not specified, the model will output text.

Risposta

OK, the request was successful.

Represents a chat completion response returned by model, based on the provided input.

​
id
string
obbligatorio

A unique identifier for the chat completion.

​
model
string
obbligatorio

The model used for the chat completion.

​
object
enum<string>
obbligatorio

The object type, which is always chat.completion.

Opzioni disponibili:
chat.completion
​
choices
object[]
obbligatorio

A list of chat completion choices. Can be more than one if n is greater than 1.

​
created
number
obbligatorio

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

​
system_fingerprint
string

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.