Skip to content

ChatGPT โ€‹

Updated

Endpoint: https://mmu.vod-qcloud.com/v1Auth: VOD ApiToken / Bearer

ChatGPT is a text generation / chat model called through an OpenAI-compatible API, with JSON and SSE streaming responses. It supports the Chat Completions, Responses, and Messages protocols and offers the GPT-4.x / GPT-5.x families, covering general chat, coding, and reasoning.

Basic information โ€‹

ItemValue
Call addresshttps://mmu.vod-qcloud.com
AuthThe VOD application's issued ApiToken / Bearer
OutputText / structured response
Response methodJSON / SSE

Callable models โ€‹

Model IDProtocol
gpt-chat-latestChat Completions / Responses / Messages
gpt-6.1-sol NEWChat Completions / Responses / Messages
gpt-6-solChat Completions / Responses / Messages
gpt-6-lunaChat Completions / Responses / Messages
gpt-6-astraChat Completions / Responses / Messages
gpt-5.6-terraChat Completions / Responses / Messages
gpt-5.6-solChat Completions / Responses / Messages
gpt-5.6-lunaChat Completions / Responses / Messages
gpt-5.5Chat Completions / Responses / Messages
gpt-5.4-proChat Completions / Responses / Messages
gpt-5.4-nanoChat Completions / Responses / Messages
gpt-5.4-miniChat Completions / Responses / Messages
gpt-5.4Chat Completions / Responses / Messages
gpt-5.3-codexChat Completions / Responses / Messages
gpt-5.3-chatChat Completions / Responses / Messages
gpt-5.2-chatChat Completions / Responses / Messages
gpt-5.2Chat Completions / Responses / Messages
gpt-5.1-chatChat Completions / Responses / Messages
gpt-5.1Chat Completions / Responses / Messages
gpt-5-nanoChat Completions / Responses / Messages
gpt-5-miniChat Completions / Responses / Messages
gpt-5-chatChat Completions / Responses / Messages
gpt-5Chat Completions / Responses / Messages
gpt-4oChat Completions / Responses / Messages
gpt-4.1Chat Completions / Responses / Messages

In https://text-aigc.vod-qcloud.com/v1/chat/completions, the VOD ApiToken also lets you use JSON responses and SSE streaming. Chat Completions streaming requests use stream=true and stream_options.include_usage=true.

Supported protocols โ€‹

SpecificationPathTarget
Chat CompletionsPOST /v1/chat/completionsAll models below
ResponsesPOST /v1/responsesAll models below
MessagesPOST /v1/messagesAll models below

All ChatGPT models listed in this document support Responses on the WAND gateway. Input fields per protocol follow API Reference.

Sampling options by version โ€‹

Model IDtemperaturetop_p
gpt-chat-latestNot supportedNot supported
gpt-6-solSettable when reasoning.effort=noneSettable when reasoning.effort=none
gpt-6-lunaSettable when reasoning.effort=noneSettable when reasoning.effort=none
gpt-6-astraNot supportedNot supported
gpt-5.6-terraSettable when reasoning.effort=noneSettable when reasoning.effort=none
gpt-5.6-solSettable when reasoning.effort=noneSettable when reasoning.effort=none
gpt-5.6-lunaSettable when reasoning.effort=noneSettable when reasoning.effort=none
gpt-5.5Settable when reasoning.effort=noneSettable when reasoning.effort=none
gpt-5.4-proNot supportedNot supported
gpt-5.4-nanoSettableSettable
gpt-5.4-miniSettableSettable
gpt-5.4SettableSettable
gpt-5.3-codexSettableSettable
gpt-5.3-chatNot supportedNot supported
gpt-5.2-chatNot supportedNot supported
gpt-5.2SettableSettable
gpt-5.1-chatNot supportedNot supported
gpt-5.1SettableSettable
gpt-5-nanoNot supportedNot supported
gpt-5-miniNot supportedNot supported
gpt-5-chatNot supportedNot supported
gpt-5Not supportedNot supported
gpt-4oSettableSettable
gpt-4.1SettableSettable

temperature sets the sampling temperature, and top_p sets the cumulative probability range. Center your tuning on one method.

Reasoning settings by version โ€‹

Model IDHow to setDisable
gpt-chat-latestReasoning settings not supportedโ€”
gpt-6-solreasoning.effortnone
gpt-6-lunareasoning.effortnone
gpt-6-astrareasoning.effortCannot be disabled
gpt-5.6-terrareasoning.effortnone
gpt-5.6-solreasoning.effortnone
gpt-5.6-lunareasoning.effortnone
gpt-5.5reasoning.effortnone
gpt-5.4-proreasoning.effortCannot be disabled
gpt-5.4-nanoreasoning.effortnone
gpt-5.4-minireasoning.effortnone
gpt-5.4reasoning.effortnone
gpt-5.3-codexreasoning.effortnone
gpt-5.3-chatReasoning settings not supportedโ€”
gpt-5.2-chatReasoning settings not supportedโ€”
gpt-5.2reasoning.effortnone
gpt-5.1-chatReasoning settings not supportedโ€”
gpt-5.1reasoning.effortnone
gpt-5-nanoreasoning.effortCannot be disabled
gpt-5-minireasoning.effortCannot be disabled
gpt-5-chatReasoning settings not supportedโ€”
gpt-5reasoning.effortCannot be disabled
gpt-4oReasoning settings not supportedโ€”
gpt-4.1Reasoning settings not supportedโ€”

The Responses baseline field is reasoning.effort. In Chat Completions, use reasoning_effort. For models that cannot be disabled, specify the reasoning effort allowed by that version.

Reasoning and token limits by version โ€‹

Model IDReasoning effortContext tokensMax output tokens
gpt-6-solnone / low / medium / high / xhigh / max1,050,000128,000
gpt-6-lunanone / low / medium / high / xhigh / max1,050,000128,000
gpt-6-astralow / medium / high / xhigh / max1,050,000128,000
gpt-5.6-terranone / low / medium / high / xhigh / max1,050,000128,000
gpt-5.6-solnone / low / medium / high / xhigh / max1,050,000128,000
gpt-5.6-lunanone / low / medium / high / xhigh / max1,050,000128,000
gpt-5.5none / low / medium / high / xhigh1,050,000128,000
gpt-5.4-promedium / high / xhigh1,050,000128,000
gpt-5.4-nanonone / low / medium / high / xhigh400,000128,000
gpt-5.4-mininone / low / medium / high / xhigh400,000128,000
gpt-5.4none / low / medium / high / xhigh1,050,000128,000
gpt-5.3-codexDefault setting400,000128,000
gpt-5.2none / low / medium / high / xhigh400,000128,000
gpt-5.1none / low / medium / high400,000128,000
gpt-5-nanoDefault setting400,000128,000
gpt-5-miniDefault setting400,000128,000
gpt-5minimal / low / medium / high400,000128,000
gpt-4oDefault setting128,00016,384
gpt-4.1Default settingknowledge1,047,576

Request parameters โ€‹

ParameterRequiredTypeDescription
modelRequiredStringModel ID in the callable-model and per-version option tables
messagesRequiredArrayConversation input for Chat Completions / Messages
inputRequiredString / ArrayInput for Responses. Used instead of messages
max_tokensOptionalIntegerGeneration limit for Chat Completions / Messages. Required in Messages
max_output_tokensOptionalIntegerGeneration limit for Responses
streamOptionalBooleantrue: SSE / false: JSON

Request examples โ€‹

GPT 6.1 Sol Chat CompletionsNEW โ€‹

json
{
  "model": "gpt-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": "Compute 17 + 25. Reply with the number only."
    }
  ],
  "max_tokens": 256,
  "stream": false
}

Response โ€‹

json
{
  "object": "chat.completion",
  "model": "gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "42"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 19,
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    },
    "prompt_cached_tokens_details": {
      "audio_tokens": 0
    },
    "completion_tokens": 5,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "total_tokens": 24
  }
}

Chat Completions โ€‹

json
{
  "model": "gpt-chat-latest",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK and nothing else."
    }
  ],
  "max_tokens": 512,
  "stream": false
}

Response โ€‹

json
{
  "id": "01a0de31-615d-7014-9372-2ab6ab19e70e",
  "object": "chat.completion",
  "model": "gpt-chat-latest",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OK"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    },
    "prompt_cached_tokens_details": {
      "audio_tokens": 0
    },
    "completion_tokens": 17,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "total_tokens": 31
  }
}

Responses โ€‹

json
{
  "model": "gpt-6-astra",
  "input": "Reply with exactly OK and nothing else.",
  "max_output_tokens": 2048,
  "stream": false,
  "reasoning": {
    "effort": "low"
  }
}

Response โ€‹

json
{
  "id": "resp_06ba8773e2ed38cf006ab7df36befc8195ab2906ff31076da8",
  "object": "response",
  "model": "gpt-6-astra",
  "status": "completed",
  "output": [
    {
      "id": "msg_06ba8773e2ed38cf006ab7df37be88819585df66bae9e722a1",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": ,
          "logprobs": ,
          "text": "OK"
        }
      ],
      "phase": "final_answer",
      "role": "assistant"
    }
  ],
  "usage": {
    "input_tokens": 14,
    "input_tokens_details": {
      "cache_write_tokens": 0,
      "cached_tokens": 0
    },
    "output_tokens": 5,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 19
  }
}

Messages โ€‹

json
{
  "model": "gpt-chat-latest",
  "messages": [
    {
      "role": "user",
      "content": "Reply with exactly OK and nothing else."
    }
  ],
  "max_tokens": 512,
  "stream": false
}

Response โ€‹

json
{
  "id": "01a0de34-7483-76a8-a2e6-5f997dc8388c",
  "model": "gpt-chat-latest",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "text": "OK",
      "type": "text"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 14,
    "output_tokens": 5
  }
}

Special settings โ€‹

Chat Completions uses reasoning_effort, and Responses uses reasoning.effort. Specify reasoning settings to match the model version. gpt-6-astra and Pro models do not use the none that turns reasoning off; instead they use the effort allowed by that version.

Responses' output can contain reasoning items and message items together. type=message's content holds type=output_text as the text. Chat Completions reads choices.message.content.

GPT-6 Sol tool calls use the Responses specification. Function calls in Chat Completions are composed with reasoning_effort=none. Native tools and gateway-compatible fields are separate.

Additional options by version โ€‹

Call gpt-5.4-pro and gpt-5.3-codex through the Responses path. Specify reasoning effort with reasoning.effort.

Built with VitePress ยท Deployed on Tencent EdgeOne Pages