chat_completion

Generate conversational responses using DeepSeek's language models with customizable parameters like temperature, max tokens, and penalties for context-aware and adaptive interactions.

Input Schema

Name	Required	Default
`frequency_penalty`	No
`max_tokens`	No
`message`	No
`messages`	No
`model`	No	deepseek-reasoner
`presence_penalty`	No
`temperature`	No
`top_p`	No

Input Schema (JSON Schema)

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "frequency_penalty": {
      "default": 0.1,
      "maximum": 2,
      "minimum": -2,
      "type": "number"
    },
    "max_tokens": {
      "default": 8000,
      "exclusiveMinimum": 0,
      "type": "integer"
    },
    "message": {
      "type": "string"
    },
    "messages": {
      "items": {
        "additionalProperties": false,
        "properties": {
          "content": {
            "type": "string"
          },
          "role": {
            "enum": [
              "system",
              "user",
              "assistant"
            ],
            "type": "string"
          }
        },
        "required": [
          "role",
          "content"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "model": {
      "default": "deepseek-reasoner",
      "type": "string"
    },
    "presence_penalty": {
      "default": 0,
      "maximum": 2,
      "minimum": -2,
      "type": "number"
    },
    "temperature": {
      "default": 0.7,
      "maximum": 2,
      "minimum": 0,
      "type": "number"
    },
    "top_p": {
      "default": 1,
      "maximum": 1,
      "minimum": 0,
      "type": "number"
    }
  },
  "type": "object"
}

DeepSeek MCP Server

chat_completion

Input Schema

Input Schema (JSON Schema)

Other Tools from DeepSeek MCP Server

Related Tools

MCP directory API