Text generation

POST 
/api/v5/chat/completions

Request

Header Parameters

Authorization stringrequired

User Personal Token

application/json

Body

temperatureTemperature (number)
Default 0.7
top_ktop_k (integer)
Default 50
top_ptop_p (number)
Default 0.7
frequency_penaltynumber
Default 1.0
messagesstring[]required
modelModel (string)required
maxTokensMaximum Token Count (integer)

Responses

200

Response Headers

application/json

Schema

Schema

trace_idString (string)required

Unique identifier of the request

choicesstring[]required

extstringrequired

Extended field, usually null

usage objectrequired

prompt_tokens1 (integer)required

Token count for the prompt

completion_tokens1 (integer)required

Token count required to complete the content

total_tokens1 (integer)required

Total token count

think_tokens1 (integer)

The number of token consumed in the thinking process

Example (auto)

{
  "trace_id": "string",
  "choices": [
    "string"
  ],
  "ext": "string",
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "think_tokens": 0
  }
}

Example

{
  "trace_id": "045560649c7c483e80eb196e2bc95d38",
  "choices": [
    {
      "index": 0,
      "finish_reason": null,
      "delta": {
        "content": "This is a fragment of streaming content."
      }
    }
  ],
  "ext": null,
  "usage": {
    "prompt_tokens": 11,
    "completion_tokens": 146,
    "total_tokens": 157,
    "think_tokens": null
  }
}