Create Chat Completion DeepSeek v3.1 Thinking Degree (Streaming)

POST https://www.kkiai.com/v1/chat/completions

Request Parameters

Authorization

Add the Authorization parameter to the Header. Its value is the Token concatenated after Bearer.

Example: Authorization: Bearer ********************

Header Parameters

Parameter Name	Type	Required	Description	Example
Content-Type	string	Required		application/json
Accept	string	Required		application/json
Authorization	string	Optional		Bearer {{YOUR_API_KEY}}
X-Forwarded-Host	string	Optional		localhost:5173

Body Parameters (application/json)

Parameter Name	Type	Required	Description
model	string	Required	The ID of the model to use.
max_tokens	integer	Optional	Limit the maximum number of tokens the model can generate in a completion for a single request. The total length of input tokens and output tokens is limited by the model's context length.
messages	array[object]	Required
└ role	string	Required
└ content	string	Required
temperature	integer	Optional	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 the output more focused and deterministic.
stream	boolean	Optional	If set to True, messages will be sent as stream increments in the form of SSE (server-sent events). The message stream ends with data: [DONE].
stream_options	object	Optional	Options related to streaming output. This parameter can only be set when the stream parameter is true.
└ include_usage	boolean	Optional	If set to true, an additional chunk will be transmitted before data: [DONE] at the end of the streaming message. The usage field on this chunk shows token usage statistics for the entire request, while the choices field will always be an empty array. All other chunks will also contain a usage field, but its value will be null.
thinking	object	Optional	Some models with deep thinking capabilities support controlling whether to disable deep thinking through the thinking field.
└ type	string	Optional	enabled: Default, forcibly enables deep thinking capability. disabled: Forcibly disables deep thinking capability. auto: The model determines whether to perform deep thinking.

Request Example

{
  "model": "deepseek-v3-1-250821",
  "max_tokens": 1000,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "temperature": 1.0,
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
     "thinking":{
         "type":"enabled"
     }
}

cURL Example

curl --location --request POST 'https://www.kkiai.com/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "deepseek-v3-1-250821",
  "max_tokens": 1000,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "temperature": 1.0,
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
     "thinking":{
         "type":"enabled"
     }
}'

Response

🟢 200 OK

Response Body

Parameter Name	Type	Required	Description
id	string	Required
object	string	Required
created	integer	Required
choices	array[object]	Required
└ index	integer	Optional
└ message	object	Optional
└ finish_reason	string	Optional
usage	object	Required
└ prompt_tokens	integer	Required
└ completion_tokens	integer	Required
└ total_tokens	integer	Required

Response Example

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}