MaaS_GP_5.5

Basic information

Project	Description
Base URL	https://genaiapi.cloudsway.net/v1/
Authentication method	Bearer Token (API Key)
Response format	JSON
Request format	JSON

Request parameters

Parameter	Type	Required	Description
model	string	is	Model name
messages	array	is	Conversation Message List
temperature	float	No	Sampling temperature (0-2), default 1.0
top_p	float	No	Nucleus sampling parameter (0-1), default 1.0
max_tokens	int	No	Maximum number of generated tokens
stream	boolean	No	Whether to stream output, default false
presence_penalty	float	No	-2.0 to 2.0
frequency_penalty	float	No	-2.0 to 2.0
seed	int	No	Deterministic Generation Seed

Example of GPT 5.5 Call

/responses: Non-streaming synchronous request

curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer ${YOUR_AK} " \
    -d '{
        "input": [
            {
                "role": "developer",
                "content": "Talk like a pirate."
            },
            {
                "role": "user",
                "content": "Are semicolons optional in JavaScript?"
            }
        ]
    }'

/responses: Streaming Synchronous Request

curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer ${YOUR_AK} " \
    -d '{
        "input": [
            {
                "role": "developer",
                "content": "Talk like a pirate."
            },
            {
                "role": "user",
                "content": "Are semicolons optional in JavaScript?"
            }
        ],
        "stream": true
    }'

/responses: Non-streaming asynchronous request

curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer ${YOUR_AK} " \
    -d '{
        "background": true,
        "input": [
            {
                "role": "developer",
                "content": "Talk like a pirate."
            },
            {
                "role": "user",
                "content": "Are semicolons optional in JavaScript?"
            }
        ]
    }'

/responses: Streaming Asynchronous Requests

curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer ${YOUR_AK} " \
    -d '{
        "background": true,
        "stream": true,
        "input": [
            {
                "role": "developer",
                "content": "Talk like a pirate."
            },
            {
                "role": "user",
                "content": "Are semicolons optional in JavaScript?"
            }
        ]
    }'

/responses: Get asynchronous request results

curl --location --request GET 'https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/responses/{responseId}' \
--header 'Authorization: Bearer ${YOUR_AK} ' \
--header 'Content-Type: application/json' \
--data-raw '{
}'

/chat/completions

/chat/completions Non-streaming Request

curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer ${YOUR_AK} " \
    -d '{
        "input": [
            {
                "role": "developer",
                "content": "Talk like a pirate."
            },
            {
                "role": "user",
                "content": "Are semicolons optional in JavaScript?"
            }
        ]
    }'

Response Example

{
    "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 Streaming Request

curl "https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer ${YOUR_AK} " \
    -d '{
        "messages": [
            {
                "role": "developer",
                "content": "Talk like a pirate."
            },
            {
                "role": "user",
                "content": "Are semicolons optional in JavaScript?"
            }
        ],
        "stream": true
    }'

Inference Model

Official Website: https://developers.openai.com/api/docs/guides/reasoning?lang=curl

Effort	Most suitable for...
none	For latency-sensitive tasks, if there is no benefit from any inference or multi-chain tool call, gpt-5.5 recommends trying it first, and then switching to low if necessary. Common application scenarios include voice, rapid information retrieval, and classification. none
low	Efficient reasoning with slightly increased latency. Very suitable for application scenarios that require the use of tools, planning, searching, or multi-step decision-making, while balancing speed and cost. Common application scenarios include Data Analysis, drafting, execution-oriented coding, and customer support/chat assistant workflows.
medium	When quality and reliability are crucial, and the task involves planning, complex reasoning, and judgment, this solution is the ideal choice. It is the default configuration for most workloads and a balance point on the Pareto curve of latency, performance, and cost. (The default inference effort level is medium) Common use cases include intelligent coding, research, handling spreadsheets and slides, and delegating long-term tasks.
high	Suitable for scenarios that require complex reasoning, complex debugging, in-depth planning, and high-value tasks, where quality and intelligence are more important than latency. Recommended for complex workflows and agent tasks. Common use cases include agent coding, long-term research, and knowledge work. Depending on the complexity of the task, evaluate between medium and high.
xhigh	Deep research, asynchronous workflows, and agent tasks that require long deployment times. They are only used when the evaluation results show that their advantages are significant enough to offset the additional latency and cost. Common use cases include security and code review, enterprise productivity, deep research tasks, and complex coding workflows.

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?"
  }'

Return Result:

{
    "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
}