Chat Completions

Core endpoint, compatible with OpenAI Chat Completions API format.

POST

https://www.ciyuano.com/v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID, e.g. deepseek-v4-flash, mimo-v2.5-pro, auto
`messages`	array	Yes	Message list containing conversation history
`stream`	boolean	No	Enable streaming output, default false
`temperature`	number	No	Sampling temperature, range 0-2, default 1
`top_p`	number	No	Nucleus sampling probability, range 0-1
`max_tokens`	integer	No	Maximum output tokens
`frequency_penalty`	number	No	Frequency penalty, range -2 to 2
`presence_penalty`	number	No	Presence penalty, range -2 to 2
`stop`	string / array	No	Stop sequences
`tools`	array	No	Tool list for Function Calling
`tool_choice`	string / object	No	Tool selection strategy: auto / none / required / specific function

Message Object Format

Field	Type	Description
`role`	string	system / user / assistant / tool
`content`	string / array	Message content. String for text, array for multimodal (images)
`tool_calls`	array	Tool calls returned by the model (assistant role)
`tool_call_id`	string	Tool call ID (required for tool role)

Request Example

JSON

{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "temperature": 0.7,
  "max_tokens": 2048
}

Response Example

JSON

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 12,
    "total_tokens": 32
  }
}