MaaS_GP_5.5
基本信息
| 项目 | 说明 |
|---|---|
| 基础URL | https://genaiapi.cloudsway.net/v1/ |
| 认证方式 | Bearer Token (API Key) |
| 响应格式 | JSON |
| 请求格式 | JSON |
请求参数
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
model |
string | 是 | 模型名称 |
messages |
array | 是 | 对话消息列表 |
temperature |
float | 否 | 采样温度 (0-2),默认1.0 |
top_p |
float | 否 | 核采样参数 (0-1),默认1.0 |
max_tokens |
int | 否 | 最大生成token数 |
stream |
boolean | 否 | 是否流式输出,默认false |
presence_penalty |
float | 否 | -2.0 到 2.0 |
frequency_penalty |
float | 否 | -2.0 到 2.0 |
seed |
int | 否 | 确定性生成种子 |
GPT 5.5 调用示例
/responses:非流式同步请求
curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_API_KEY}" \
-d '{
"input": [
{
"role": "developer",
"content": "Talk like a pirate."
},
{
"role": "user",
"content": "Are semicolons optional in JavaScript?"
}
]
}'
/responses:流式同步请求
curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_API_KEY}" \
-d '{
"input": [
{
"role": "developer",
"content": "Talk like a pirate."
},
{
"role": "user",
"content": "Are semicolons optional in JavaScript?"
}
],
"stream": true
}'
/responses:非流式异步请求
curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_API_KEY}" \
-d '{
"background": true,
"input": [
{
"role": "developer",
"content": "Talk like a pirate."
},
{
"role": "user",
"content": "Are semicolons optional in JavaScript?"
}
]
}'
/responses:流式异步请求
curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_API_KEY}" \
-d '{
"background": true,
"stream": true,
"input": [
{
"role": "developer",
"content": "Talk like a pirate."
},
{
"role": "user",
"content": "Are semicolons optional in JavaScript?"
}
]
}'
/responses:获取异步请求结果
curl --location --request GET 'https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses/{responseId}' \
--header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \
--data-raw '{
}'
/chat/completions
/chat/completions 非流式请求
curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_API_KEY}" \
-d '{
"input": [
{
"role": "developer",
"content": "Talk like a pirate."
},
{
"role": "user",
"content": "Are semicolons optional in JavaScript?"
}
]
}'
响应示例
{
"id": "chatcmpl-DaF0J1KUc86StE3bCpt3bnopw0KKi",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Arrr, semicolons in JavaScript be **mostly optional**, but not because the language ignores ’em — because JavaScript has **Automatic Semicolon Insertion**, or **ASI**, which adds semicolons in certain places for ye.\n\nSo this works:\n\n```js\nconst x = 1\nconst y = 2\nconsole.log(x + y)\n```\n\nSame as:\n\n```js\nconst x = 1;\nconst y = 2;\nconsole.log(x + y);\n```\n\nBut beware, matey: ASI can surprise ye.\n\nExample:\n\n```js\nreturn\n{\n value: 42\n}\n```\n\nJavaScript treats it like:\n\n```js\nreturn;\n{\n value: 42\n}\n```\n\nSo the function returns `undefined`, not the object.\n\nAnother common danger:\n\n```js\nconst x = 1\n[1, 2, 3].forEach(console.log)\n```\n\nThis can be parsed like:\n\n```js\nconst x = 1[1, 2, 3].forEach(console.log)\n```\n\nwhich be trouble.\n\nA safe version:\n\n```js\nconst x = 1;\n[1, 2, 3].forEach(console.log);\n```\n\nOr, if ye prefer no semicolons, start risky lines with a defensive semicolon:\n\n```js\nconst x = 1\n;[1, 2, 3].forEach(console.log)\n```\n\nSo: **Aye, semicolons are usually optional, but not always harmless to omit.** Many crews either use semicolons consistently or follow a style guide that avoids ASI traps.",
"annotations": []
},
"finish_reason": "stop",
"native_finish_reason": "stop"
}
],
"created": 1777529855,
"model": "MaaS_GP_5.5_20260424",
"object": "chat.completion",
"service_tier": "default",
"usage": {
"prompt_tokens": 24,
"completion_tokens": 375,
"total_tokens": 399,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0,
"reasoning_tokens": 25,
"rejected_prediction_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0
}
}
}
/chat/completions 流式请求
curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_API_KEY}" \
-d '{
"messages": [
{
"role": "developer",
"content": "Talk like a pirate."
},
{
"role": "user",
"content": "Are semicolons optional in JavaScript?"
}
],
"stream": true
}'
推理模型
官方网址:https://developers.openai.com/api/docs/guides/reasoning?lang=curl
| Effort | 最适合…… |
|---|---|
| none | 对于延迟敏感型任务,如果无法从任何推理或多链工具调用中获益,gpt-5.5则建议先尝试使用,如果需要low再切换到。常见的应用场景包括语音、快速信息检索和分类。none |
| low | 高效推理,延迟略有增加。非常适合需要使用工具、进行规划、搜索或多步骤决策的应用场景,同时兼顾速度和成本。 常见应用场景包括数据分析、草拟、面向执行的编码以及客户支持/聊天助手工作流程。 |
| medium | 当质量和可靠性至关重要,且任务涉及规划、复杂推理和判断时,此方案是理想之选。它是大多数工作负载的默认配置,也是延迟、性能和成本帕累托曲线上的一个平衡点。(默认的推理effort 程度是medium) 常见用例包括智能编码、研究、处理电子表格和幻灯片以及委派长期工作。 |
| high | 适用于需要进行复杂推理、复杂调试、深度规划以及高价值任务的情况,在这些任务中,质量和智能比延迟更为重要。推荐用于复杂的工作流程和智能体任务。 常见用例包括智能体编码、长期研究和知识工作。根据任务的复杂性,评估medium两者high。 |
| xhigh | 深度研究、异步工作流程和需要长时间部署的代理任务。仅当评估结果显示其优势明显,足以抵消额外的延迟和成本时才使用。 常见用例包括安全和代码审查、企业生产力、深度研究任务以及复杂的编码工作流程。 |
curl https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.5",
"reasoning": {"effort": "medium"},
"input": "What is the weather like today?"
}'
返回结果:
{
"id": "resp_0e2f0fc8cbccc4a70069f2f35639088196b86db02840f771a6",
"metadata": {},
"model": "MaaS_GP_5.5_20260424",
"output": [
{
"id": "rs_0e2f0fc8cbccc4a70069f2f356cb2881968a474232d814fc31",
"type": "reasoning",
"summary": []
},
{
"id": "msg_0e2f0fc8cbccc4a70069f2f357ced081969f556a82d5e254d2",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I can help—what city or location would you like the weather for?"
}
],
"phase": "final_answer",
"role": "assistant"
}
],
"temperature": 1.0,
"tools": [],
"background": false,
"reasoning": {
"effort": "medium"
},
"status": "completed",
"text": {
"format": {
"type": "text"
},
"verbosity": "medium"
},
"truncation": "disabled",
"usage": {
"input_tokens": 13,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 39,
"output_tokens_details": {
"reasoning_tokens": 18
},
"total_tokens": 52
},
"store": true,
"created_at": 1777529686,
"object": "response",
"parallel_tool_calls": true,
"tool_choice": "auto",
"top_p": 0.98,
"completed_at": 1777529688,
"prompt_cache_retention": "in_memory",
"service_tier": "default",
"top_logprobs": 0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0
}