Skip to content

MaaS_Hy

Model Specifications

Capability Description context window Maximum Input Maximum Output
New-generation productivity model, with comprehensive upgrades in Agent and complex task execution capabilities 1024k 960k 64k

Request Protocol

https

Header (Public)

Parameter Name Type Required Description
Content-Type string Yes application/json
Authorization string Yes Bearer ${your_AK}

OpenAI Chat Completions

Request URL

POST https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions

Request Body Parameters

Parameter Name Secondary Parameters Three-level parameter Type Required Description
model - - string Yes Fixed as MaaS_Hy_4_preview_20260828
messages - - array[json] Yes Chat context, sequence:[system (optional) → user → assistant → user →. ..]
role - string Yes system / user / assistant / tool
content - string Yes Plain text; Hy4 does not support image_url/video_url/file_url
reasoning_content - string No Chain of Thought; fill back as-is when multi-turn + tool calling is involved
tool_calls - array No Tool Call List
tool_call_id - string Conditions Required when role= tool
stream - - boolean No Streaming output (SSE), default false
stream_options - - object No Only takes effect when stream= trueis configured
include_usage - boolean No Whether the last chunk in streaming contains usage, default is false
temperature - - float No [0.0,2.0], default value is 1.0
top_p - - float No (0.0,1.0], default 1.0
max_tokens - - integer No Maximum output tokens, ≥ 1, upper limit 64k
max_completion_tokens - - integer No Same as max_tokens, pass either of the two
n
 - - integer No Default value is 1; must be 1 when the thinking mode is enabled
stop - - string or array No Stop sequences, maximum 4
seed - - integer No random seed
frequency_penalty - - float No [-2.0,2.0], default value 0
presence_penalty - - float No [-2.0,2.0], default value 0
thinking - - object No Deep Thinking; enabled by default for Hy4
type - string conditions "enabled" / "disabled"
budget_tokens - integer No Max tokens for reasoning; defaults to 8192 if not specified
reasoning_effort - - string No Inference depth; default high, supports none, high
response_format - - object No Response format, default{"type":"text"}
type - string Yes text / json_object / json_schema
json_schema - object conditions type= json_schemamandatory when applicable
- name string Yes Schema Name
- schema object Yes JSON Schema
- strict boolean No Exact match, defaults to false
tools - - array No Function Calling Tool List
type - string Yes Fixed "function"
function - object Yes function definition
- name string Yes function name
- description string No function description
- parameters object No JSON Schema Input Parameters
tool_choice - - string or object No Default "auto"
parallel_tool_calls - - boolean No Parallel tool invocation, default value is true
user - - string No End User Identifier

Request Example

curl -X POST 'https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ${your_AK}' \
  -d '{
    "model": "MaaS_Hy_4_preview_20260828",
    "messages": [
      {"role": "user", "content": "Hello, please briefly introduce yourself."}
    ],
    "stream": false,
    "temperature": 0.9,
    "reasoning_effort": "high"
  }'

Response Example

{
  "id": "chatcmpl-xxxxxxxx",
  "object": "chat.completion",
  "model": "MaaS_Hy_4_preview_20260828",
  "created": 1775146513,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I am Hunyuan, a large language model developed by Tencent...",
        "reasoning_content": "The user asked me to briefly introduce myself..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 221,
    "total_tokens": 249,
    "completion_tokens_details": {"reasoning_tokens": 175}
  }
}

Example of streaming request

curl -X POST 'https://genaiapi.cloudsway.net/v1/ai/{endpointPath}/chat/completions' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ${your_AK}' \
  -d '{
    "model": "MaaS_Hy_4_preview_20260828",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

SDK Invocation Method

from openai import OpenAI

client = OpenAI(
    api_key="${your_AK}",
    base_url="https://genaiapi.cloudsway.net/v1/ai/{endpointPath}",
)

response = client.chat.completions.create(
    model="MaaS_Hy_4_preview_20260828",
    messages=[{"role": "user", "content": "Hello, please briefly introduce yourself."}],
    temperature=0.9,
    extra_body={"reasoning_effort": "high"},
)
print(response.choices[0].message.content)

OpenAI Responses

Request URL

POST https://genaiapi.cloudsway.net/v1/ai/{endpoint}/responses

Request Body Parameters

Parameter Name Secondary Parameters Type Required Description
model - string Yes Fixed as MaaS_Hy_4_preview_20260828
input - string or array Yes Plain text string, or an array of input entries
instructions - string No System/Developer Instructions
stream - boolean No SSE Streaming
max_output_tokens - number No Maximum output tokens (including inference tokens), ≥ 1
temperature - number No [0, 2]
top_p - number No (0, 1]
truncation - string No "auto"/ "disabled"(default)
tools - array No Tool array; compatibility mode only supports function
tool_choice - string or object No "none"/ "auto"/ specified function
parallel_tool_calls - boolean No Whether to call tools in parallel
text - object No Output Format Control
format object No text / json_schema / json_object
reasoning - object No Inference Model Configuration
effort string No "none" / "low" / "medium" / "high"
summary string No "auto" / "concise" / "detailed"
metadata - object No Additional metadata (up to 16 key-value pairs)

Request Example

curl -X POST 'https://genaiapi.cloudsway.net/v1/ai/{endpoint}/responses' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ${your_AK}' \
  -d '{
    "model": "MaaS_Hy_4_preview_20260828",
    "input": "Hello, please briefly introduce yourself.",
    "reasoning": {"effort": "high"}
  }'

Response Example

{
  "id": "resp_xxxxxxxx",
  "object": "response",
  "created_at": 1741476542,
  "status": "completed",
  "model": "MaaS_Hy_4_preview_20260828",
  "output": [
    {
      "type": "reasoning",
      "summary": [{"type": "summary_text", "text": "User requested self-introduction..."}]
    },
    {
      "type": "message",
      "role": "assistant",
      "content": [{"type": "output_text", "text": "I am Hunyuan, a large language model developed by Tencent..."}]
    }
  ],
  "usage": {
    "input_tokens": 20,
    "output_tokens": 221,
    "total_tokens": 241
  }
}

Stream Request Example

curl -X POST 'https://genaiapi.cloudsway.net/v1/ai/{endpoint}/responses' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ${your_AK}' \
  -d '{
    "model": "MaaS_Hy_4_preview_20260828",
    "input": "Hello",
    "stream": true
  }'

SDK Calling Method

from openai import OpenAI

client = OpenAI(
    api_key="${your_AK}",
    base_url="https://genaiapi.cloudsway.net/v1/ai/{endpoint}",
)

response = client.responses.create(
    model="MaaS_Hy_4_preview_20260828",
    input="Hello, please briefly introduce yourself.",
    extra_body={"reasoning": {"effort": "high"}},
)
print(response.output_text)

Anthropic Messages

Request URL

POST https://genaiapi.cloudsway.net/{endpoint}/v1/messages

Header (Additional to This Agreement)

Parameter Name Type Required Description
anthropic-version string Yes 2023-06-01

Request Body Parameters

Parameter Name Secondary Parameters Three-level parameter Band 4 Parameters Type Required Description
model - - - string Yes Fixed as MaaS_Hy_4_preview_20260828
messages - - - array[json] Yes Conversation message list with complete context
role - - string Yes user / assistant
content - - string or array Yes Plain text string, or content block array
- type - string No textetc.
- text - string No type= texttext when applicable
system - - - string or array No System prompt (top-level field, not included in messages)
max_tokens - - - integer Yes Maximum output tokens per run; the chain-of-thought tokens count towards this limit
stream - - - boolean No Streaming SSE, default false
temperature - - - float No [0,1](Anthropic range)
top_p - - - float No (0, 1]
top_k - - integer No Only sample from the top K tokens
stop_sequences - - - string[] No Custom Stop Sequences
tools - - - array No Tool Definition (Flat Structure)
name - - string Yes Tool Name
description - - string No Tool Description
input_schema - - object Yes JSON Schema Input Parameters
tool_choice - - - object No {"type":"auto"} / none / any / specified tool
thinking - - - object No Extended Chain of Thought
type - - string conditions "enabled" / "disabled"
budget_tokens - - integer No Chain-of-Thought Token Budget

Request Example

curl -X POST 'https://genaiapi.cloudsway.net/{endpoint}/v1/messages' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ${your_AK}' \
  -H 'anthropic-version: 2023-06-01' \
  -d '{
    "model": "MaaS_Hy_4_preview_20260828",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, please briefly introduce yourself."}
    ]
  }'

Response Example

{
  "id": "msg_xxxxxxxx",
  "type": "message",
  "role": "assistant",
  "model": "MaaS_Hy_4_preview_20260828",
  "content": [
    {"type": "thinking", "thinking": "User requested self-introduction..."},
    {"type": "text", "text": "I am Hunyuan, a large language model developed by Tencent..."}
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 28,
    "output_tokens": 221
  }
}

Example of streaming request

curl -X POST 'https://genaiapi.cloudsway.net/{endpoint}/v1/messages' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer ${your_AK}' \
  -H 'anthropic-version: 2023-06-01' \
  -d '{
    "model": "MaaS_Hy_4_preview_20260828",
    "max_tokens": 1024,
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

SDK Invocation Method

import httpx

response = httpx.post(
    "https://genaiapi.cloudsway.net/{endpoint}/v1/messages",
    headers={
        "Authorization": "Bearer ${your_AK}",
        "Content-Type": "application/json",
        "anthropic-version": "2023-06-01",
    },
    json={
        "model": "MaaS_Hy_4_preview_20260828",
        "max_tokens": 1024,
        "messages": [{"role": "user", "content": "Hello, please briefly introduce yourself."}],
    },
)
print(response.json())