MaaS_Gr

Request Protocol

https

Header

Parameter Name	Type	Required	Description
Content-Type	string	is	Fixed to applicatio n/json
Authorization	string	is	Bearer {your_api_key}

Request URL

POST https://{新平台域名}/v1/ai/{endpointPath}/happyhorse/v1/video-synthesis

Request Body Parameters

Attribute Name	Type	Required/Optional	Description
deferred	boolean or null	Optional (default false)	If set to true, the request returns request_id, and then the deferred response can be obtained via GET /v1/chat/deferred-completion/{request_id}.
frequency_penalty	number or null	Optional (default 0, range -2 to 2)	Penalty value based on the existing frequency of tokens. A positive value reduces the probability of repeating the same line. (Not supported by inference models)
logit_bias	object or null	Optional	(not supported by reasoning models) A JSON object that maps token IDs to bias values ranging from -100 to 100.
logprobs	boolean or null	Optional (default false)	Whether to return the log probabilities of the output tokens.
max_completion_tokens	integer or null	Optional	Maximum number of tokens to generate for completion (only applies to visible output tokens, excluding inference or function call tokens).
max_tokens	integer or null	Optional (deprecated)	is deprecated, it is recommended to use max_completion_tokens.
messages	array	Required	Conversation message list. Each message contains role ( system/user/assistant/tool/function) and content (can be a string or an array of content components, supporting text, image URLs, file IDs, etc.).
model	string	Required	Name of the model used.
n	integer or null	Optional (default 1, minimum 1)	Number of completion choices generated for each input message.
parallel_tool_calls	boolean or null	Optional (default true)	If false, the model executes at most one tool call.
presence_penalty	number or null	Optional (default 0, range -2 to 2)	Penalty value based on whether the new token has already appeared. Positive values encourage the model to discuss new topics. (Not supported by grok-3and inference models)
reasoning_effort	string or null	Optional	Limit the intensity of the inference model's thinking. Optional low (using fewer inference tokens) or high (using more inference tokens). Not supported for grok-4.
response_format	object or null	Optional	Structured output format. Can specify text, json_object, or a detailed structure with json_schema.
search_parameters	object or null	Optional	Parameters that control real-time data retrieval. Includes mode (off/on/auto), sources (x, web, news, rss), date range, citation return, etc.
seed	integer or null	Optional	Deterministic sampling seed (strives to ensure that the same parameters return the same results, not absolute).
stop	array or null	Optional	Up to 4 stop sequences, generation stops upon encountering them. (Not supported by inference model)
stream	boolean or null	Optional (default false)	Whether to enable streaming response. Once enabled, incremental messages will be sent in SSE format.
stream_options	object or null	Optional	Streaming option. Includes include_usage (sends an additional block containing usage before ending).
temperature	number or null	Optional (default 1, range 0\~2)	Sampling temperature. A higher value makes the output more random, while a lower value makes it more deterministic.
tool_choice	string or object or null	Optional	Controls how the model selects tools. "none" / "auto" / "required" or specify a specific function name.
tools	array or null	Optional	List of tools that the model can call (currently supports function type). Up to 128 functions, each containing a name, description, and parameter JSON schema.
top_logprobs	integer or null	Optional (range 0\~8)	Returns the top K most likely tokens and their log probabilities at each token position. logprobs=true must be set simultaneously.
top_p	number or null	Optional (default 1, range 0\~1, excluding 0)	Nucleus sampling probability mass. Usually adjusted in combination with temperature as an alternative.
user	string or null	Optional	Unique Device Identifier for end users for monitoring and abuse detection.
web_search_options	object or null	Optional	Fields retained solely for OpenAI compatibility, containing filters, search_context_size, and user_location.

Call Example

/chat/completions

/chat/completions Non-streaming Request

curl --location --request POST 
'https://{新平台域名}/v1/ai/{endpointPath}/chat/completions' \
--header 'Authorization: Bearer {api key}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "grok-4.3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "thinking": {"type": "enabled"},
    "reasoning_effort": "high",
    "stream": false
}'

/chat/completions Streaming Request

curl --location --request POST 
'https://{新平台域名}/v1/ai/{endpointPath}/chat/completions' \
--header 'Authorization: Bearer {api key}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "grok-4.3",
    "stream": true,
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "thinking": {"type": "enabled"},
    "reasoning_effort": "high",
    "stream": false
}'

Unified Domain Access /v1/chat/completions

Curl Request

curl --location 'https://genaiapi.cloudsway.net/v1/chat/completions' \
--header 'Authorization: Bearer YOUR_ACCESS_KEY' \
--header 'Content-Type: application/json' \
--data '{

    "messages": [
        {
            "role": "user", 
            "content": [
                {
                    "type": "text", 
                    "text": "hi"
                }
            ]
        }
    ], 
    "model":"MaaS_Gr_4.3_20260501",
    "stream": false,
    "stream_options":{"include_usage":true}
}'

Python Request

import requests
import json

YOUR_ACCESS_KEY = "YOUR_ACCESS_KEY"

url = "https://genaiapi.cloudsway.net/v1/chat/completions"

headers = {
    "Authorization": f"Bearer {YOUR_ACCESS_KEY}",
    "Content-Type": "application/json"
}

payload = {
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "hi"
                }
            ]
        }
    ],
    "model": "MaaS_Gr_4.3_20260501",
    "stream": False,
    "stream_options": {"include_usage": True}
}

try:
    response = requests.post(url, headers=headers, json=payload)
    response.raise_for_status() 
    print(response.json())       
except requests.exceptions.RequestException as e:
    print(f"请求失败: {e}")

Return Example

{
    "id": "a6ce483d-99b6-9910-a25a-69ff67e41e45",
    "choices": [
        {
            "index": 0,
            "logprobs": null,
            "message": {
                "role": "assistant",
                "content": "Hi! How can I help you today?",
                "refusal": null,
                "annotations": null,
                "images": null,
                "reasoning_content": "The user said \"hi\". This is a simple greeting. As an AI, I should respond in a friendly, engaging way.\n",
                "function_call": null,
                "tool_calls": null,
                "reasoning_details": null
            },
            "finish_reason": "stop",
            "native_finish_reason": null
        }
    ],
    "logprobs": null,
    "created": 1779095005,
    "model": "MaaS_Gr_4.3_20260501",
    "object": "chat.completion",
    "system_fingerprint": "fp_f06c287374635121",
    "service_tier": null,
    "usage": {
        "prompt_tokens": 131,
        "completion_tokens": 126,
        "total_tokens": 257,
        "completion_tokens_details": {
            "accepted_prediction_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "reasoning_tokens": 117,
            "rejected_prediction_tokens": 0
        },
        "prompt_tokens_details": {
            "audio_tokens": 0,
            "cached_tokens": 128
        },
        "cache_creation_input_tokens": null,
        "cache_creation": null,
        "gemini_cache_tokens_details": null
    }
}