ChatGPT โ
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
| Item | Value |
|---|---|
| Call address | https://mmu.vod-qcloud.com |
| Auth | The VOD application's issued ApiToken / Bearer |
| Output | Text / structured response |
| Response method | JSON / SSE |
Callable models โ
| Model ID | Protocol |
|---|---|
gpt-chat-latest | Chat Completions / Responses / Messages |
gpt-6.1-sol NEW | Chat Completions / Responses / Messages |
gpt-6-sol | Chat Completions / Responses / Messages |
gpt-6-luna | Chat Completions / Responses / Messages |
gpt-6-astra | Chat Completions / Responses / Messages |
gpt-5.6-terra | Chat Completions / Responses / Messages |
gpt-5.6-sol | Chat Completions / Responses / Messages |
gpt-5.6-luna | Chat Completions / Responses / Messages |
gpt-5.5 | Chat Completions / Responses / Messages |
gpt-5.4-pro | Chat Completions / Responses / Messages |
gpt-5.4-nano | Chat Completions / Responses / Messages |
gpt-5.4-mini | Chat Completions / Responses / Messages |
gpt-5.4 | Chat Completions / Responses / Messages |
gpt-5.3-codex | Chat Completions / Responses / Messages |
gpt-5.3-chat | Chat Completions / Responses / Messages |
gpt-5.2-chat | Chat Completions / Responses / Messages |
gpt-5.2 | Chat Completions / Responses / Messages |
gpt-5.1-chat | Chat Completions / Responses / Messages |
gpt-5.1 | Chat Completions / Responses / Messages |
gpt-5-nano | Chat Completions / Responses / Messages |
gpt-5-mini | Chat Completions / Responses / Messages |
gpt-5-chat | Chat Completions / Responses / Messages |
gpt-5 | Chat Completions / Responses / Messages |
gpt-4o | Chat Completions / Responses / Messages |
gpt-4.1 | Chat 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
| Specification | Path | Target |
|---|---|---|
| Chat Completions | POST /v1/chat/completions | All models below |
| Responses | POST /v1/responses | All models below |
| Messages | POST /v1/messages | All 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 ID | temperature | top_p |
|---|---|---|
gpt-chat-latest | Not supported | Not supported |
gpt-6-sol | Settable when reasoning.effort=none | Settable when reasoning.effort=none |
gpt-6-luna | Settable when reasoning.effort=none | Settable when reasoning.effort=none |
gpt-6-astra | Not supported | Not supported |
gpt-5.6-terra | Settable when reasoning.effort=none | Settable when reasoning.effort=none |
gpt-5.6-sol | Settable when reasoning.effort=none | Settable when reasoning.effort=none |
gpt-5.6-luna | Settable when reasoning.effort=none | Settable when reasoning.effort=none |
gpt-5.5 | Settable when reasoning.effort=none | Settable when reasoning.effort=none |
gpt-5.4-pro | Not supported | Not supported |
gpt-5.4-nano | Settable | Settable |
gpt-5.4-mini | Settable | Settable |
gpt-5.4 | Settable | Settable |
gpt-5.3-codex | Settable | Settable |
gpt-5.3-chat | Not supported | Not supported |
gpt-5.2-chat | Not supported | Not supported |
gpt-5.2 | Settable | Settable |
gpt-5.1-chat | Not supported | Not supported |
gpt-5.1 | Settable | Settable |
gpt-5-nano | Not supported | Not supported |
gpt-5-mini | Not supported | Not supported |
gpt-5-chat | Not supported | Not supported |
gpt-5 | Not supported | Not supported |
gpt-4o | Settable | Settable |
gpt-4.1 | Settable | Settable |
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 ID | How to set | Disable |
|---|---|---|
gpt-chat-latest | Reasoning settings not supported | โ |
gpt-6-sol | reasoning.effort | none |
gpt-6-luna | reasoning.effort | none |
gpt-6-astra | reasoning.effort | Cannot be disabled |
gpt-5.6-terra | reasoning.effort | none |
gpt-5.6-sol | reasoning.effort | none |
gpt-5.6-luna | reasoning.effort | none |
gpt-5.5 | reasoning.effort | none |
gpt-5.4-pro | reasoning.effort | Cannot be disabled |
gpt-5.4-nano | reasoning.effort | none |
gpt-5.4-mini | reasoning.effort | none |
gpt-5.4 | reasoning.effort | none |
gpt-5.3-codex | reasoning.effort | none |
gpt-5.3-chat | Reasoning settings not supported | โ |
gpt-5.2-chat | Reasoning settings not supported | โ |
gpt-5.2 | reasoning.effort | none |
gpt-5.1-chat | Reasoning settings not supported | โ |
gpt-5.1 | reasoning.effort | none |
gpt-5-nano | reasoning.effort | Cannot be disabled |
gpt-5-mini | reasoning.effort | Cannot be disabled |
gpt-5-chat | Reasoning settings not supported | โ |
gpt-5 | reasoning.effort | Cannot be disabled |
gpt-4o | Reasoning settings not supported | โ |
gpt-4.1 | Reasoning settings not supported | โ |
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 ID | Reasoning effort | Context tokens | Max output tokens |
|---|---|---|---|
gpt-6-sol | none / low / medium / high / xhigh / max | 1,050,000 | 128,000 |
gpt-6-luna | none / low / medium / high / xhigh / max | 1,050,000 | 128,000 |
gpt-6-astra | low / medium / high / xhigh / max | 1,050,000 | 128,000 |
gpt-5.6-terra | none / low / medium / high / xhigh / max | 1,050,000 | 128,000 |
gpt-5.6-sol | none / low / medium / high / xhigh / max | 1,050,000 | 128,000 |
gpt-5.6-luna | none / low / medium / high / xhigh / max | 1,050,000 | 128,000 |
gpt-5.5 | none / low / medium / high / xhigh | 1,050,000 | 128,000 |
gpt-5.4-pro | medium / high / xhigh | 1,050,000 | 128,000 |
gpt-5.4-nano | none / low / medium / high / xhigh | 400,000 | 128,000 |
gpt-5.4-mini | none / low / medium / high / xhigh | 400,000 | 128,000 |
gpt-5.4 | none / low / medium / high / xhigh | 1,050,000 | 128,000 |
gpt-5.3-codex | Default setting | 400,000 | 128,000 |
gpt-5.2 | none / low / medium / high / xhigh | 400,000 | 128,000 |
gpt-5.1 | none / low / medium / high | 400,000 | 128,000 |
gpt-5-nano | Default setting | 400,000 | 128,000 |
gpt-5-mini | Default setting | 400,000 | 128,000 |
gpt-5 | minimal / low / medium / high | 400,000 | 128,000 |
gpt-4o | Default setting | 128,000 | 16,384 |
gpt-4.1 | Default setting | knowledge | 1,047,576 |
Request parameters โ
| Parameter | Required | Type | Description |
|---|---|---|---|
model | Required | String | Model ID in the callable-model and per-version option tables |
messages | Required | Array | Conversation input for Chat Completions / Messages |
input | Required | String / Array | Input for Responses. Used instead of messages |
max_tokens | Optional | Integer | Generation limit for Chat Completions / Messages. Required in Messages |
max_output_tokens | Optional | Integer | Generation limit for Responses |
stream | Optional | Boolean | true: SSE / false: JSON |
Request examples โ
GPT 6.1 Sol Chat CompletionsNEW โ
{
"model": "gpt-6.1-sol",
"messages": [
{
"role": "user",
"content": "Compute 17 + 25. Reply with the number only."
}
],
"max_tokens": 256,
"stream": false
}Response โ
{
"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
{
"model": "gpt-chat-latest",
"messages": [
{
"role": "user",
"content": "Reply with exactly OK and nothing else."
}
],
"max_tokens": 512,
"stream": false
}Response โ
{
"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
{
"model": "gpt-6-astra",
"input": "Reply with exactly OK and nothing else.",
"max_output_tokens": 2048,
"stream": false,
"reasoning": {
"effort": "low"
}
}Response โ
{
"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
{
"model": "gpt-chat-latest",
"messages": [
{
"role": "user",
"content": "Reply with exactly OK and nothing else."
}
],
"max_tokens": 512,
"stream": false
}Response โ
{
"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.