Skip to content

DeepSeek โ€‹

Updated

Endpoint: https://mmu.vod-qcloud.com/v1Authentication: VOD ApiToken / Bearer

DeepSeek is a text generation / chat model called through an OpenAI-compatible API, with JSON and SSE streaming responses. It supports the Chat Completions and Messages protocols, offers versions such as v4-pro and v4.1-flash, and can enable reasoning (thinking) mode as needed.

Basic Information โ€‹

ItemValue
Call endpointhttps://mmu.vod-qcloud.com
AuthenticationVOD Application-issued ApiToken / Bearer
OutputText / Structured response
Response modeJSON / SSE

Supported Protocols โ€‹

SpecPathTarget
Chat CompletionsPOST /v1/chat/completionsAll models below
MessagesPOST /v1/messagesAll models below

The model IDs below use the corresponding spec. Authentication and common fields follow API Reference.

Sampling Options โ€‹

Commonly applies to all models listed in this document.

ParameterSetting
temperatureConfigurable
top_pConfigurable

temperature specifies the sampling temperature, and top_p specifies the cumulative probability range. Adjust centered on one method.

Per-Version Reasoning Settings โ€‹

Model IDConfigurationDisable
deepseek-v4.1-flashthinking_enabledfalse
deepseek-v4-prothinking_enabledfalse
deepseek-v4-flashthinking_enabledfalse
deepseek-v3.2thinking_enabledfalse
deepseek-flashthinking_enabledfalse

Based on Chat Completions. Reasoning content is read from reasoning_content, and the final answer from content. Do not pass a disable option to versions that cannot be disabled.

Request Parameters โ€‹

ParameterRequiredTypeDescription
modelRequiredStringA model ID from the per-version options table
messagesRequiredArrayConversation input for Chat Completions / Messages
max_tokensOptionalIntegerGeneration limit for Chat Completions / Messages. Required in Messages
streamOptionalBooleantrue: SSE / false: JSON

Request Examples โ€‹

Chat Completions โ€‹

json
{
  "model": "deepseek-v4.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK and nothing else."
    }
  ],
  "max_tokens": 2048,
  "stream": false,
  "reasoning_effort": "low"
}

Response โ€‹

json
{
  "id": "01a0de40-cd17-7102-8a8d-82c46dd1e693",
  "object": "chat.completion",
  "model": "deepseek-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK",
        "reasoning_content": "We need answer exactly OK and nothing else. Must comply. Final \"OK\"."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 38,
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    },
    "prompt_cached_tokens_details": {
      "audio_tokens": 0
    },
    "completion_tokens": 18,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 16,
      "rejected_prediction_tokens": 0
    },
    "total_tokens": 56
  }
}

Messages โ€‹

json
{
  "model": "deepseek-v4.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK and nothing else."
    }
  ],
  "max_tokens": 512,
  "stream": false
}

Response โ€‹

json
{
  "id": "01a0de32-ad83-7af6-97ee-7b98a0bd1513",
  "model": "deepseek-flash",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "text": "OK",
      "type": "text"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 38,
    "output_tokens": 17
  }
}

Special Settings โ€‹

Reasoning and the final answer are returned in reasoning_content and content respectively. Pass the previous turn's final answer through assistant.content to continue the conversation. Support for thinking_enabled and reasoning_effort applies per version.

The tool_calls.function.arguments of a function call is a JSON string. After parsing it, run the tool and connect the result with the corresponding tool_call_id.

Built with VitePress ยท Deployed on Tencent EdgeOne Pages