Basic Information
-
Base URL: https://genaiapi.cloudsway.net
-
API request endpoint:
POST -
Authentication: Verified via the HTTP Bearer Token method, and the API key needs to be carried in the request header.
| Parameter Name | Type | Required | Description |
|---|---|---|---|
Content-Type |
string | Yes | Fixed as application/json |
Authorization |
string | Yes | Bearer {your_api_key} |
Core Parameter Description
Official Chat Completions API Documentation of OpenAI
Request Parameters
| field | Meaning | Hierarchy | Format | Required | Note |
|---|---|---|---|---|---|
| messages | The list of messages that make up the current conversation | 1 | arrary | Yes | Depending on the model used, different types of message content (modalities) are supported, including text, images and audio. |
| Developer message | Instructions provided by the developer that the model should always follow, regardless of whatever messages the user sends | 2 | object | For models o1 and later versions, developer messages replace the previous system messages. | |
| content | Content of Developer Messages | 3 | string or array | Yes | |
| Text content | Content of Developer Messages | 4 | string | ||
| Array of content parts | An array of content blocks defined by a specific type | 4 | array | For developer messages, only the text type (text) is supported | |
| text | Text content | 5 | string | Yes | |
| type | Content Block Type | 5 | string | Yes | |
| role | Role of the Message Author | 3 | string | Yes | Here is the developer |
| name | An optional name for the participant, which is used to provide information to the model to distinguish different participants with the same role. | 3 | string | ||
| System message | Instructions provided by the developer, which the model should follow regardless of what message the user sends | 2 | object | For models of version o1 and later, please use developer messages to implement this feature instead | |
| content | System Message Content | 3 | string or array | Yes | |
| Text content | System Message Content | 4 | string | ||
| Array of content parts | An array of content blocks defined by a specific type | 4 | array | For system messages, only the text type (text) is supported | |
| Text content part | Text content | 5 | object | ||
| text | Text content | 6 | string | Yes | |
| type | Content Block Type | 6 | string | Yes | |
| role | Role of the Message Author | 3 | string | Yes | Here is the system |
| name | An optional name for the participant, which is used to provide information to the model to distinguish different participants with the same role. | 3 | string | ||
| User message | The message sent by the end user, which contains a prompt or additional context information | 2 | object | ||
| content | Content of the user's message | 3 | string or array | Yes | |
| Text content | Content of the user's message | 4 | string | ||
| Array of content parts | An array of content blocks defined by a specific type | 4 | array | The supported content types vary depending on the model used to generate the response, and may include text, image or audio inputs. | |
| Text content part | Text content | 5 | object | ||
| text | Text content | 6 | string | Yes | |
| type | Type of content block | 6 | string | Yes | |
| Image content part | 5 | object | |||
| imageurl | 6 | object | Yes | ||
| url | URL of the image or base64-encoded image data | 7 | stirng | Yes | |
| detail | Specify the level of detail for the image | 7 | stirng | Defaults to auto | |
| type | Type of content block | 6 | string | Yes | |
| role | Role of the message author | 3 | string | Yes | Here is the user |
| name | Optional name for the participant, which is used to provide information to the model to distinguish different participants with the same role | 3 | string | ||
| Assistant message | A message sent by the model in response to a user message | 2 | object | ||
| role | Role of the message author | 3 | string | Yes | Here is the assistant |
| audio | Data related to the model's previous audio response | 3 | object or null | ||
| id | Unique Device Identifier of the model's previous audio response | 4 | string | Yes | |
| content | Content of the assistant's message | 3 | string or array | Required field unless toolcalls or functioncall is specified | |
| Text content | Text content of the assistant message | 4 | string | ||
| Array of content parts | Array of content blocks with defined types | 4 | array | It may contain one or more text-type content blocks, or exactly one refusal-type content block | |
| Text content part | 5 | object | |||
| text | Text content | 6 | string | Yes | |
| type | Content Block Type | 6 | string | Yes | |
| Refusal content part | 5 | object | |||
| refusal | Rejection message generated by the model | 6 | string | Yes | |
| type | Content Block Type | 6 | string | Yes | |
| functioncall | Deprecated, replaced by toolcalls | 3 | object or null | Contains the name and parameters of the function to be called generated by the model | |
| name | The name of the function to be called | 4 | string | Yes | |
| arguments | The parameters used when calling the function are generated by the model in JSON format. | 4 | string | Yes | Note: The JSON generated by the model is not necessarily valid and may contain parameters not defined in the function schema. Please validate the parameters before calling the function. |
| name | An optional name for the participant, used to distinguish between different participants with the same role | 3 | string | ||
| refusal | Assistant's rejection message | 3 | string or null | ||
| toolcalls | Tool calls generated by the model (such as function calls) | 3 | array | ||
| Function tool call | Calling the function tool created by the model | 4 | object | ||
| function | The function called by the model | 5 | object | Yes | |
| arguments | The parameters required when calling a function are generated by the model in JSON format | 6 | string | Yes | Please note that the content generated by the model is not always valid JSON, and it may fabricate parameters that are not defined in the function schema. Therefore, validate these parameters in your code before calling the function. |
| name | The name of the function to be called | 6 | string | Yes | |
| id | ID of the tool call | 5 | string | Yes | |
| type | Currently, only the function type is supported for tools | 5 | string | Yes | |
| Tool message | 2 | object | |||
| content | Content of tool messages | 3 | string or array | Yes | |
| Text content | Text content of the tool message | 4 | string | ||
| Array of content parts | An array of content blocks of a specific type. Only the text type is supported for tool messages. | 4 | array | ||
| Text content part | 5 | object | |||
| text | Text content | 6 | string | Yes | |
| type | Content Block Type | 6 | string | Yes | |
| role | The role of the message author, which is tool here | 3 | string | Yes | |
| toolcallid | The ID of the tool call that this message is responding to | 3 | string | Yes | |
| model | The model ID used to generate the response, such as gpt-4o or o3 | 1 | string | Yes | |
| frequencypenalty | A value between -2.0 and 2.0, with a default of 0 | 1 | number or null | Positive values penalize based on the existing frequency of the token in the current text, thereby reducing the likelihood that the model will repeat the same content verbatim. | |
| logitbias | Adjust the occurrence probability of the specified token in the generated result, which defaults to null | 1 | map | Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to a bias value between -100 and 100. Mathematically, this bias is added to the model's logits right after they are generated and before sampling. The exact effect varies by model, but in general: - Values between -1 and 1 will slightly decrease/increase the selection probability of the corresponding token - Extreme values such as -100 or 100 will completely ban or force the selection of the token | |
| maxcompletiontokens | The maximum allowed number of tokens in the generated result (including visible output tokens and inference tokens) | 1 | integer or null | ||
| n | The number of chat completion options generated for each input message, which defaults to 1 | 1 | integer or null | Note: The fee will be calculated based on the total number of tokens generated for all options, and it is recommended to keep n= 1 to control costs | |
| paralleltoolcalls | Specifies whether to enable parallel function invocation when using the tool; the default value is true | 1 | boolean | ||
| presencepenalty | A value between -2.0 and 2.0, with a default of 0 | 1 | number or null | Positive values penalize based on whether a token has already appeared in the current text, thereby increasing the likelihood that the model will discuss new topics | |
| responseformat | An object that specifies the output format of the model | 1 | object | ||
| Text | Default Text Response Format | 2 | object | ||
| type | The defined response format type. Always text | 3 | string | Yes | |
| JSON schema | JSON Schema response format, used to generate structured JSON responses | 2 | object | ||
| jsonschema | Configuration options for structured output, including a JSON schema | 3 | object | Yes | |
| name | The name of the response format. It must consist of a-z, A-Z, 0-9, or contain underscores and hyphens, with a maximum length of 64 characters. | 4 | string | Yes | |
| description | A description of the purpose of this response format, for the model to determine how to respond in this format | 4 | string | ||
| schema | The schema of the response format, described in the form of a JSON schema object | 4 | object | ||
| strict | Whether to enable strict schema adherence when generating the output. Defaults to false; if set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true | 4 | boolean or null | ||
| type | The type of response format, which is fixed as jsonobject | 3 | string | Yes | |
| JSON object | JSON Object Response Format | 2 | object | This is a relatively outdated method for generating JSON responses. For models that support jsonschema, it is recommended to use jsonschema. Note that the model will not generate JSON unless there is a system message or a user message instructing it to do so. | |
| type | The type of response format defined. It is always a jsonobject. | 3 | string | Yes | |
| seed | (Deprecated) If this parameter is specified, the system will try its best to implement deterministic sampling (repeated requests with the same seed and parameters should return the same result). Determinism is not guaranteed, and backend changes need to be monitored via the systemfingerprint response parameter | 1 | integer or null | This feature is currently in the testing phase | |
| stop | The latest reasoning models o3 and o4-mini do not support this parameter, and its default value is null. | 1 | string/array/null | Up to 4 stop sequences can be set, and the output will be terminated when the API generates these sequences (the returned text does not include the stop sequences themselves) | |
| store | Whether to store the output of this chat completion request for model distillation or product evaluation, the default value is false | 1 | boolean or null | Supports text and image input. Note: Image inputs larger than 10MB will be discarded. | |
| stream | If set to true, the model response data will be streamed via Server-Sent Events (SSE); the default value is false. | 1 | boolean or null | ||
| streamoptions | Optional parameters for streaming response (only valid when stream is set to true; defaults to null) | 1 | object or null | ||
| includeobfuscation | When stream obfuscation is enabled (true by default), random characters are added to streaming events to standardize payload size (as a defense against side-channel attacks). Setting it to false saves bandwidth (ensure the network link is trusted) | 2 | boolean | ||
| includeusage | If enabled, an additional data chunk will be sent before the final data: DONE message: the usage field contains the token statistics for the entire request, and the choices field is always an empty array. Note: if the stream is interrupted, the final data chunk containing the total token consumption may not be received. | 2 | boolean | ||
| temperature | Sampling temperature (range: 0-2), default value is 1 | 1 | number or null | A higher value (e. g., 0.8) increases the randomness of the output, while a lower value (e. g., 0.2) makes the output more concentrated and deterministic. It is recommended to use this parameter as an alternative to the topp parameter. | |
| toolchoice | Controls whether (and how) the model invokes tools | 1 | string or object | none: do not call tools, generate messages directly (default when no tools available) auto: automatically choose to generate messages or call tools (default when tools are available) required: one or more tools must be called specified tool: force a specific tool to be called via {"type": "function", "function": {"name": "myfunction"}} | |
| Tool choice mode | Tool Selection Mode | 2 | string | none: generate messages directly without invoking tools (default value when no tools are available) auto: automatically choose to generate messages or invoke tools (default value when tools are available) required: one or more tools must be invoked specified tool: force the invocation of a specific tool via {"type": "function", "function": {"name": "myfunction"}} | |
| Function tool choice | Mandatorily specify the particular tool that the model should invoke | 2 | object | Used to force the model to call a specific function | |
| function | 3 | object | Yes | ||
| name | The name of the function that needs to be called | 4 | string | Yes | |
| type | Tool type: currently only function is supported | 3 | object | Yes | |
| tools | List of tools callable by the model | 1 | array | Currently, only functions are supported to be used as tools, which are used to provide a list of functions for which the model can generate JSON inputs. A maximum of 128 functions are supported. | |
| Function tool | A function tool that can be used to generate responses | 2 | object | ||
| function | 3 | object | Yes | ||
| name | The name of the called function. Only letters (a-z, A-Z), digits (0-9), underscores and hyphens are allowed, with a maximum length of 64 characters. | 4 | string | Yes | |
| description | A description of the function's capabilities, used to help the model determine when and how to invoke it | 4 | string | ||
| parameters | The parameters accepted by the function are described in JSON Schema format | 4 | object | ||
| strict | Specifies whether to enable strict mode when generating function calls. The default value is false; if set to true, the model will strictly follow the JSON Schema structure defined in parameters. | 4 | boolean or null | Only partial JSON Schema features are supported in strict mode | |
| type | Tool type. Currently only function is supported | 3 | string | Yes | |
| topp | An alternative to temperature sampling — nucleus sampling: the model only considers tokens whose cumulative probability mass falls within the top-p range. The default value is 1. | 1 | number or null | For example, a value of 0.1 means only the tokens corresponding to the top 10% of probability mass are considered. Recommendation: adjust this parameter or temperature, but do not adjust both at the same time |
Return Result
Returns a chat completion object, or a stream of chat completion chunk objects if streaming is enabled in the request.
OpenAI endpoint-style request API
POSThttps://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions
Sample Request and Response Results
curl request
curl https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${your_AK}" \
-d '{
"model": "gpt-5",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
Response Result
{
"id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
"object": "chat.completion",
"created": 1741569952,
"model": "gpt-4.1-2025-04-14",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 10,
"total_tokens": 29,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}
OpenAI integrates Chat Completion request API
POST https://genaiapi.cloudsway.net/v1/chat/completions
Sample Request and Response Results
curl request
curl https://genaiapi.cloudsway.net/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${your_AK}" \
-d '{
"model": "{MaaS Moddel Name}",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
Response Result
curl https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${your_AK}" \
-d '{
"model": "gpt-5",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
Official Response API Documentation of OpenAI
Synchronization Mode
streaming request
curl 'https://genaiapi.cloudsway.net/v1/ai/{endpoint}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"input": "1+2+n=？",
"model": "gpt-o3-pro-2025-06-10",
"stream": true,
"reasoning": {
"effort": "high",
"summary": "auto"
}
}'
Tool call invocation
First Request
curl 'https://genaiapi.cloudsway.net/v1/ai/{endpoint}/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer ${your_AK}' \
--data '{
"model": "MaaS-o3-mini-2025-01-31",
"input": "What is the weather like in Boston today?",
"tools": [
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location", "unit"]
}
}
],
"tool_choice": "auto"
}'
Response
{
"id": "resp_68906124c3f08190995b6b59b54bc1300718351d629a7990",
"object": "response",
"created_at": 1754292516,
"status": "completed",
"background": false,
"content_filters": null,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"max_tool_calls": null,
"model": "MaaS-o3-mini-2025-01-31",
"output": [
{
"id": "rs_6890612fc9448190be00d13682364ca30718351d629a7990",
"type": "reasoning",
"summary": []
},
{
"id": "fc_6890612fcb44819086adeb804dbd6dbf0718351d629a7990",
"type": "function_call",
"status": "completed",
"arguments": "{\"location\":\"Boston, MA\",\"unit\":\"fahrenheit\"}",
"call_id": "call_8KWaObBBaHuJsbGcgEQ6OWFK",
"name": "get_current_weather"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"prompt_cache_key": null,
"reasoning": {
"effort": "medium",
"summary": null
},
"safety_identifier": null,
"service_tier": "default",
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "function",
"description": "Get the current weather in a given location",
"name": "get_current_weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
]
}
},
"required": [
"location",
"unit"
]
},
"strict": true
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 77,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 28,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 105
},
"user": null,
"metadata": {}
}
Second Request
curl 'https://genaiapi.cloudsway.net/v1/ai/{endpoint}/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer ${your_AK}' \
--data '{
"model": "MaaS-o3-mini-2025-01-31",
"input": [
{
"role": "user",
"content": "What is the weather like in Boston today?"
},
{
"id": "rs_6890612fc9448190be00d13682364ca30718351d629a7990",
"type": "reasoning",
"summary": []
},
{
"id": "fc_6890612fcb44819086adeb804dbd6dbf0718351d629a7990",
"type": "function_call",
"call_id": "call_8KWaObBBaHuJsbGcgEQ6OWFK",
"name": "get_current_weather",
"arguments": "{\"location\":\"Boston, MA\",\"unit\":\"fahrenheit\"}"
},
{
"type": "function_call_output",
"call_id": "call_8KWaObBBaHuJsbGcgEQ6OWFK",
"output": "68"
}
],
"tools": [
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location", "unit"]
}
}
]
}'
Response
{
"id": "resp_6890637dcef081909a45e5996c1004d20718351d629a7990",
"object": "response",
"created_at": 1754293117,
"status": "completed",
"background": false,
"content_filters": null,
"error": null,
"incomplete_details": null,
"instructions": null,
"max_output_tokens": null,
"max_tool_calls": null,
"model": "MaaS-o3-mini-2025-01-31",
"output": [
{
"id": "msg_6890638be07481909fe137356876ea180718351d629a7990",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"text": "The current temperature in Boston is 68 °F."
}
],
"role": "assistant"
}
],
"parallel_tool_calls": true,
"previous_response_id": null,
"prompt_cache_key": null,
"reasoning": {
"effort": "medium",
"summary": null
},
"safety_identifier": null,
"service_tier": "default",
"store": true,
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"tool_choice": "auto",
"tools": [
{
"type": "function",
"description": "Get the current weather in a given location",
"name": "get_current_weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
]
}
},
"required": [
"location",
"unit"
]
},
"strict": true
}
],
"top_p": 1.0,
"truncation": "disabled",
"usage": {
"input_tokens": 180,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 15,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 195
},
"user": null,
"metadata": {}
}
Thinking Mode Request
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"input": "1+2+n=？",
"model": "MaaS-o3-mini-2025-01-31",
"reasoning": {
"effort": "high",
"summary": "detailed"
}
}'
Thinking Pattern Response
{
"id": "resp_68904df39c0c8190a11c8a48c8f84957006db06e07770eb8",
"model": "MaaS-o3-mini-2025-01-31",
"background": false,
"instructions": null,
"object": "response",
"output": [
{
"summary": [
{
"type": "summary_text",
"text": "**Simplifying an expression**\n\nI see the user is asking for the result of 1 + 2 + n. Without context, I can just give them the symbolic expression: 3 + n. If n is an integer, it might help to ask for clarification about n, but since it's unknown, the result remains 3 + n. The user may initially want to see that mathematical expression, so I’ll present it as 3 + n with that explanation. This all seems straightforward."
}
],
"type": "reasoning",
"id": "rs_68904e02c9488190b84ddd71c371c68d006db06e07770eb8"
},
{
"role": "assistant",
"type": "message",
"content": [
{
"annotations": [],
"type": "output_text",
"text": "Without knowing the value of n, the sum remains symbolic:\n\n1 + 2 + n = 3 + n"
}
],
"id": "msg_68904e05d5b481909afe35fbcb122312006db06e07770eb8",
"status": "completed"
}
],
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"created_at": 1754287603,
"error": null,
"incomplete_details": null,
"max_output_tokens": null,
"metadata": {},
"output_text": null,
"parallel_tool_calls": true,
"previous_response_id": null,
"reasoning": {
"effort": "high",
"summary": "detailed"
},
"status": "completed",
"tool_choice": "auto",
"tools": [],
"top_p": 1.0,
"truncation": "disabled",
"user": null,
"usage": {
"input_tokens": 12,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 93,
"output_tokens_details": {
"reasoning_tokens": 64
},
"total_tokens": 105
}
}
image recognition
URL-formatted request
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"model": "MaaS-o3-mini-2025-01-31",
"input": [
{
"role": "user",
"content": [
{"type": "input_text", "text": "Describe the content in this image"},
{
"type": "input_image",
"image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
]
}
]
}'
base64 formatted request
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"model": "MaaS-o3-mini-2025-01-31",
"input": [
{
"role": "user",
"content": [
{"type": "input_text", "text": "Describe the content in this image"},
{
"type": "input_image",
"image_url": "data:image/png;base64,iVBORwxxxx"
}
]
}
]
}'
Multi-turn Dialogue Request
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"input": "What is 1+1?",
"model": "MaaS-o3-mini-2025-01-31",
"reasoning": {
"effort": "high",
"summary": "detailed"
}
}'
Response
{
"id": "resp_6892f0b52de48190951e6b39e336957b03dd80b38745bdda",
"model": "MaaS-o3-mini-2025-01-31",
"background": false,
"instructions": null,
"object": "response",
"output": [
{
"summary": [],
"type": "reasoning",
"id": "rs_6892f0c957308190bbda9ea58c26186f03dd80b38745bdda"
},
{
"role": "assistant",
"type": "message",
"content": [
{
"annotations": [],
"type": "output_text",
"text": "1+1 equals 2."
}
],
"id": "msg_6892f0c9588c81908fdbb97e05cd07b503dd80b38745bdda",
"status": "completed"
}
],
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"created_at": 1754460341,
"error": null,
"incomplete_details": null,
"max_output_tokens": null,
"max_tool_calls": null,
"metadata": {},
"output_text": null,
"parallel_tool_calls": true,
"previous_response_id": null,
"prompt": null,
"prompt_cache_key": null,
"reasoning": {
"effort": "high",
"summary": "detailed"
},
"safety_identifier": null,
"service_tier": "default",
"status": "completed",
"tool_choice": "auto",
"tools": [],
"top_logprobs": null,
"top_p": 1.0,
"truncation": "disabled",
"user": null,
"usage": {
"input_tokens": 12,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 13,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 25
}
}
Second Request
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"input": "What is the result if you add 1 more?",
"model": "MaaS-o3-mini-2025-01-31",
"previous_response_id":"resp_6892f0b52de48190951e6b39e336957b03dd80b38745bdda",
"reasoning": {
"effort": "high",
"summary": "detailed"
}
}'
Asynchronous Mode
Request
Add "background": true to all synchronous requests, and carry the id in asynchronous GET requests
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"input": "1+2+n=？",
"background": true,
"model": "MaaS-o3-mini-2025-01-31",
"stream": true,
"reasoning": {
"effort": "high",
"summary": "detailed"
}
}'
Response
{
"id": "resp_6894071015f48190ba7629ad68d68f850427f468a587cfc8",
"model": "MaaS-o3-mini-2025-01-31",
"background": true,
"instructions": null,
"object": "response",
"output": [],
"temperature": 1.0,
"text": {
"format": {
"type": "text"
}
},
"created_at": 1754531600,
"error": null,
"incomplete_details": null,
"max_output_tokens": null,
"max_tool_calls": null,
"metadata": {},
"output_text": null,
"parallel_tool_calls": true,
"previous_response_id": null,
"prompt": null,
"prompt_cache_key": null,
"reasoning": {
"effort": "medium"
},
"safety_identifier": null,
"service_tier": "auto",
"status": "queued",
"tool_choice": "auto",
"tools": null,
"top_logprobs": null,
"top_p": 1.0,
"truncation": "disabled",
"user": null,
"usage": null
}
GET Request
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses/resp_689329c4e7e0819096e0c35b597fabe00aecb4e10eaeff14?stream=false&api-version=preview' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json'
Custom Tools
curl 'https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT}/responses' \
--header 'Authorization: Bearer ${your_AK}' \
--header 'Content-Type: application/json' \
--data '{
"model": "MaaS-o3-mini-2025-01-31",
"input": "What is the weather like in Boston today?",
"background": true,
"tools": [
{
"type": "function",
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit"
]
}
},
"required": [
"location",
"unit"
]
}
}
],
"tool_choice": {
"type": "allowed_tools",
"mode": "auto",
"tools": [
{
"type": "function",
"name": "get_current_weather"
}
]
}
}'