Chat Completions

POST /v1/chat/completions

The core conversation endpoint, compatible with the OpenAI Chat Completions format. Supports multimodal input, streaming, tool calling, and reasoning models.

Request

curl https://test.kailin.com.cn/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-token" \
  -d '{
    "model": "deepseek-v4-1-flash-261017",
    "messages": [
      { "role": "system", "content": "You are a concise assistant" },
      { "role": "user", "content": "Hello" }
    ],
    "stream": false
  }'

RequestREQUEST

POSThttps://test.kailin.com.cn/v1/chat/completions

API KeyStored only in your browser, never uploaded

Body (JSON)SSE stream · rendered live{ "model": "deepseek-v4-1-flash-261017", "messages": [ { "role": "user", "content": "Hello, introduce yourself" } ], "stream": true }

ResponseRESPONSE

Fill in the request and hit Send — the response shows up here

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model name, see List Models
messages	array	Yes	Conversation messages, see message structure below
stream	boolean	No	Stream output (SSE), default false
temperature	number	No	Sampling temperature 0–2, default 1 — lower is more deterministic
top_p	number	No	Nucleus sampling; tune this or temperature, not both
max_tokens	number	No	Max tokens to generate (newer models use max_completion_tokens)
stop	string / array	No	Stop sequences, up to 4
tools	array	No	Tool (function) definitions, see tool calling
tool_choice	string / object	No	auto / none / required / a specific tool
response_format	object	No	{"type": "json_object"} or {"type": "json_schema", ...}
seed	integer	No	Random seed for reproducibility
frequency_penalty	number	No	-2.0–2.0, reduces repetition
presence_penalty	number	No	-2.0–2.0, encourages new topics
reasoning_effort	string	No	Reasoning effort for reasoning models: low / medium / high
user	string	No	End-user identifier, useful for abuse monitoring

Message Structure

Field	Type	Description
role	string	system / user / assistant / tool
content	string / array	A string, or an array of multimodal parts (see multimodal input)
name	string	Optional participant name
tool_calls	array	Tool calls initiated by the model, on assistant messages
tool_call_id	string	Required on tool messages — the call being responded to

Response (Non-streaming)

{
  "id": "chatcmpl-B3xK1abc123",
  "object": "chat.completion",
  "created": 1730000000,
  "model": "deepseek-v4-1-flash-261017",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 12,
    "total_tokens": 32
  }
}

Field	Description
choices[].message.content	The model's reply
choices[].finish_reason	stop completed / length hit token limit / tool_calls needs tool execution
usage	Token usage — the billing basis
usage.completion_tokens_details.reasoning_tokens	Thinking tokens returned by reasoning models

Streaming Response

With "stream": true the response is an SSE event stream:

data: {"id":"chatcmpl-xxx","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Incremental content arrives in choices[].delta.content, ending with data: [DONE]. The final chunk may carry usage depending on the upstream.

Multimodal Input

Pass content as an array to mix text with images/audio. Images accept a URL or a Base64 data URL:

{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "What's in this image?" },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://upload.wikimedia.org/wikipedia/commons/3/3c/Shaki_waterfall.jpg"
          }
        }
      ]
    }
  ]
}

Content Part	Fields	Description
text	text	Text
image_url	image_url.url	Image URL or data:image/jpeg;base64,...
input_audio	input_audio.data / input_audio.format	Base64 audio (wav / mp3), model support required

Tool Calling

1. Declare tools via tools; the model responds with tool_calls.
2. Execute the tools, append results as role: "tool" messages, and call again.

{
  "model": "deepseek-v4-1-flash-261017",
  "messages": [{ "role": "user", "content": "What's the weather in Shanghai today?" }],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": { "type": "string", "description": "City name" }
          },
          "required": ["city"]
        }
      }
    }
  ]
}

Model response:

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"city\": \"Shanghai\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ]
}

After executing, send the result back:

{
  "model": "deepseek-v4-1-flash-261017",
  "messages": [
    { "role": "user", "content": "What's the weather in Shanghai today?" },
    {
      "role": "assistant",
      "tool_calls": [
        {
          "id": "call_abc123",
          "type": "function",
          "function": { "name": "get_weather", "arguments": "{\"city\": \"Shanghai\"}" }
        }
      ]
    },
    { "role": "tool", "tool_call_id": "call_abc123", "content": "Sunny, 26°C" }
  ]
}

Using the SDK

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-token",
    base_url="https://test.kailin.com.cn/v1",
)

stream = client.chat.completions.create(
    model="deepseek-v4-1-flash-261017",
    messages=[{"role": "user", "content": "Write a short poem about autumn"}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta
    if delta.content:
        print(delta.content, end="", flush=True)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-token',
  baseURL: 'https://test.kailin.com.cn/v1',
});

const stream = await client.chat.completions.create({
  model: 'deepseek-v4-1-flash-261017',
  messages: [{ role: 'user', content: 'Write a short poem about autumn' }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

note

Reasoning models (o-series, DeepSeek-R1, etc.) may return the thinking process in reasoning_content or delta.reasoning_content, depending on the upstream channel.