MaaS_GP_5.5/5.6

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 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 '{
        "messages": [
            {
                "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
}

GPT 5.6

Overview

Project	Description
Date of Issuance	2026/7/9
Model Family	Sol (flagship capability), Terra (cost-effective), Luna (high concurrency & low cost)
Alias	gpt-5.6 → routed to gpt-5.6-sol
API Support	Responses API、Chat Completions API、Batch API
Key Changes	Multiple advanced capabilities are only supported by the Responses API; the Chat Completions only retains basic inference controls

Capability × API Support Matrix (Master Table)

competence	Responses	Chat Completions	Test
Basic reasoning effort	✅ reasoning.effort	✅ reasoning_effort
Inference max effort	✅	❌	✅
Reasoning Pro Mode	✅	❌	✅
Persistent Inference	✅	❌	✅
Inference Summary	✅	❌

GPT-5.6 models support standard and pro reasoning modes in the Responses API. standard is the default. Set reasoning.mode to pro for difficult tasks that need more model work and can tolerate higher latency and token usage.

Reasoning mode and reasoning effort are independent. Mode selects standard or pro execution, while reasoning.effort controls how much reasoning the model applies within that mode. If you omit reasoning.effort, GPT-5.6 defaults to medium in both modes.

• Persisted reasoning: GPT-5.6 can reuse available reasoning items across turns to improve multi-turn quality and cache efficiency. Use reasoning.context to select the behavior.

• Max reasoning effort: GPT-5.6 supports max reasoning effort for demanding tasks that need more exploration and verification. If you currently use xhigh, compare both settings on representative workloads.

• Pro mode: GPT-5.6 can perform more model work to improve reliability on difficult tasks and return a single final answer. Enable it with reasoning.mode: "pro" when quality matters more than latency and token usage.

Request Example

curl --location --request POST 'https://genaiapi.cloudsway.net/v1/responses' \
--header 'Authorization: Bearer ${your ak}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "MaaS_GP_5.6_luna_20260709",
    "reasoning": {
      "mode": "pro",
      "context": "all_turns",
      "effort": "medium",
      "summary": "detailed"
    },
    "input": [
      {
        "role": "user",
        "content": "Review this database migration plan and identify potential failure modes."
      }
    ]
  }'

Response Example

{
    "id": "resp_0e39f8f90e030aa7006a574b155cc081938df0a6b43806e03e",
    "metadata": {},
    "model": "MaaS_GP_5.6_luna_20260709",
    "output": [
        {
            "id": "rs_0e39f8f90e030aa7006a574b1b99088193bb1371b882a93de3",
            "type": "reasoning",
            "content": [],
            "summary": [
                {
                    "type": "summary_text",
                    "text": "**Clarifying the user request**\n\nI see that the user mentioned a review but hasn't provided a plan. I think it’s important to ask them for the details. Maybe I could suggest a checklist of what’s needed to make it easier for them? That might help clarify what I need to review. I should keep it concise to ensure it’s straightforward for the user to respond. Let’s put together a request for those details!"
                }
            ]
        },
        {
            "id": "msg_0e39f8f90e030aa7006a574b1c2a3481938693b3fde82f82fe",
            "type": "message",
            "status": "completed",
            "content": [
                {
                    "type": "output_text",
                    "annotations": [],
                    "logprobs": [],
                    "text": "Please share the migration plan, including—if available:\n\n- Source and target database/schema versions\n- Tables, columns, indexes, constraints, and data transformations affected\n- Migration scripts and execution order\n- Expected data volume and downtime/maintenance window\n- Application rollout and backward-compatibility strategy\n- Backup, rollback, and recovery procedures\n- Validation and monitoring steps\n- Database engine/version and deployment environment\n\nI’ll review it for failure modes such as:\n\n- **Data loss or corruption:** incorrect transformations, truncation, encoding/time-zone issues, non-idempotent scripts\n- **Constraint failures:** foreign keys, uniqueness conflicts, invalid defaults, orphaned records\n- **Locking and availability:** long-running table locks, deadlocks, replication lag, connection exhaustion\n- **Performance regressions:** missing indexes, table rewrites, query-plan changes, excessive backfills\n- **Application incompatibility:** old code encountering new schema, new code running before migration completion\n- **Partial execution:** failures midway through multi-step migrations or across multiple services/databases\n- **Rollback gaps:** irreversible transformations, incompatible backups, rollback scripts that don’t restore application behavior\n- **Operational issues:** insufficient disk space, timeout limits, permissions, version-specific behavior\n- **Validation weaknesses:** checks that confirm migration completion but not correctness or completeness\n- **Replication and failover problems:** replica divergence, CDC incompatibility, stale reads, failover during migration\n\nPaste the plan or scripts here, and I can provide a concrete failure-mode review with severity and mitigations."
                }
            ],
            "phase": "final_answer",
            "role": "assistant"
        }
    ],
    "temperature": 1.0,
    "tools": [],
    "background": false,
    "reasoning": {
        "mode": "pro",
        "context": "all_turns",
        "effort": "medium",
        "summary": "detailed"
    },
    "status": "completed",
    "text": {
        "format": {
            "type": "text"
        },
        "verbosity": "medium"
    },
    "truncation": "disabled",
    "usage": {
        "input_tokens": 2267,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens": 890,
        "output_tokens_details": {
            "reasoning_tokens": 219
        },
        "total_tokens": 3157
    },
    "store": true,
    "created_at": 1784105749,
    "object": "response",
    "parallel_tool_calls": true,
    "tool_choice": "auto",
    "top_p": 0.98,
    "completed_at": 1784105756,
    "prompt_cache_retention": "in_memory",
    "service_tier": "default",
    "top_logprobs": 0,
    "presence_penalty": 0.0,
    "frequency_penalty": 0.0
}