Retrieve a response - Alibaba Cloud Model Studio

Replace {WorkspaceId} with your actual workspace ID.

China (Beijing)

The base_url for SDK calls is: https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1HTTP request URL: GET https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/responses/{response_id}

Path parameters

response_idstring(required)The Response ID to retrieve. The format is resp_xxx. You can get it from the response of the Create response API. Only Response IDs returned when store=true was set in the original creation request can be retrieved.

Python

import os
from openai import OpenAI

client = OpenAI(
    # If you have not configured an environment variable, replace the following line with: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
)

response = client.responses.retrieve("resp_xxx")
print(response)

Response

Returns the same Response object as the Create response API. The fields are described below:id stringUnique identifier for this response, in the format resp_xxx.object stringObject type. Always response.status stringResponse status. Possible values: completed, failed, in_progress, cancelled, queued, incomplete.created_at integerUnix timestamp (in seconds) when the response was created.completed_at integerUnix timestamp (in seconds) when the response finished generating. null if the response is not complete.error objectError object returned when the model fails to generate a response. null on success.model stringModel ID used to generate the response.output arrayOutput items generated by the model. The type and order of elements depend on the model's response.

Array element properties

type stringOutput item type. Possible values:

message: Message containing the model's final reply.
reasoning: Reasoning output. Returned when reasoning.effort is set to a value other than none or when thinking mode is enabled. Reasoning tokens are counted in output_tokens_details.reasoning_tokens and billed accordingly.
function_call: Function call output. Returned when using a custom function tool. You must handle the function call and return a result.
web_search_call: Web search call output. Returned when using the web_search tool.
code_interpreter_call: Code execution output. Returned when using the code_interpreter tool.
web_extractor_call: Web extraction output. Returned when using the web_extractor tool. Must be used together with the web_search tool.
web_search_image_call: Text-to-image search call output. Returned when using the web_search_image tool. Contains a list of images found.
image_search_call: Image-to-image search call output. Returned when using the image_search tool. Contains a list of similar images found.
mcp_call: MCP call output. Returned when using the mcp tool. Contains the result from the MCP service.
file_search_call: Knowledge base search call output. Returned when using the file_search tool. Contains retrieval queries and results from the knowledge base.

id stringUnique identifier for the output item. Present for all output types.role stringMessage role. Always assistant. Present only when type is message.status stringOutput item status. Possible values: completed, in_progress. Present when type is not reasoning.name stringTool or function name. Present when type is function_call, web_search_image_call, image_search_call, or mcp_call.For web_search_image_call and image_search_call, the value is fixed as "web_search_image" and "image_search", respectively.For mcp_call, the value is the specific function name called in the MCP service (for example, amap-maps-maps_geo).arguments stringTool call arguments, formatted as a JSON string. Present when type is function_call, web_search_image_call, image_search_call, or mcp_call. Parse it using JSON.parse() before use. Contents vary by tool type:

web_search_image_call: {"queries": ["search keyword 1", "search keyword 2"]}. The queries field contains a list of search keywords automatically generated by the model based on user input.
image_search_call: {"img_idx": 0, "bbox": [0, 0, 1000, 1000]}. The img_idx field is the index of the input image (starting from 0). The bbox field contains the bounding box coordinates [x1, y1, x2, y2] of the search area, with values ranging from 0 to 1000.
function_call: An argument object generated according to the user-defined function parameter schema.
mcp_call: An argument object for the function called in the MCP service.

call_id stringUnique identifier for the function call. Present only when type is function_call. Use this ID to associate the request with the response when returning function call results.content arrayMessage content array. Present only when type is message.

Array element properties

type stringContent type. Always output_text.text stringText content generated by the model.annotations arrayText annotations. Usually an empty array.

summary arrayReasoning summaries. Present only when type is reasoning. Each element contains a type field (value summary_text) and a text field (the summary text).action objectSearch action information. Present only when type is web_search_call.

Properties

query stringSearch query keyword.type stringSearch type. Always search.sources arraySearch sources. Each element contains a type field and a url field.

code stringCode generated and executed by the model. Present only when type is code_interpreter_call.outputs arrayCode execution outputs. Present only when type is code_interpreter_call. Each element contains a type field (value logs) and a logs field (code execution logs).container_id stringCode interpreter container identifier. Present only when type is code_interpreter_call. Use it to associate multiple code executions within the same session.goal stringDescription of the extraction goal, specifying what information to extract from the webpage. Present only when type is web_extractor_call.output stringOutput result of the tool call, formatted as a string.

When type is web_extractor_call, this field contains a summary of the extracted webpage content.
When type is web_search_image_call or image_search_call, this field is a JSON string containing an array of image search results. Each result includes a title (image title), url (image URL), and index (ordinal number) field.
When type is mcp_call, this field is a JSON string result returned by the MCP service.

urls arrayURLs of the webpages extracted. Present only when type is web_extractor_call.server_label stringMCP service label. Present only when type is mcp_call. Identifies the MCP service used for this call.queries arrayQueries used for knowledge base retrieval. Present only when type is file_search_call. Each element is a search query generated by the model.results arrayKnowledge base retrieval results. Present only when type is file_search_call.

Array element properties

file_id stringFile ID of the matched document.filename stringFilename of the matched document.score floatRelevance score, ranging from 0 to 1. Higher values indicate greater relevance.text stringSnippet of the matched document content.

usage objectToken usage information for this request.

Properties

input_tokens integerNumber of input tokens.output_tokens integerNumber of output tokens generated by the model.total_tokens integerTotal tokens used (input_tokens + output_tokens).input_tokens_details objectBreakdown of input tokens.

Properties

cached_tokens integerNumber of cached tokens.

output_tokens_details objectBreakdown of output tokens.

Properties

reasoning_tokens integerNumber of reasoning tokens.

x_details arrayBilling details.

Properties

input_tokens integerInput tokens for this billing type.output_tokens integerOutput tokens for this billing type.total_tokens integerTotal tokens for this billing type.x_billing_type stringAlways response_api.prompt_tokens_details objectReturned when session caching is enabled. Contains a cached_tokens field (number of cached tokens).

x_tools objectTool usage statistics. When built-in tools are used, this field contains the call count for each tool. Example: {"web_search": {"count": 1}}

tools arrayEchoes the tools parameter from the creation request. Structure matches the tools parameter in the request body. Empty array [] if no tools were used.tool_choice stringEchoes the tool_choice parameter from the creation request. Possible values: auto, none, required.parallel_tool_calls booleanEchoes the parallel_tool_calls parameter from the creation request. Indicates whether the model can call multiple tools in parallel.temperature floatEchoes the temperature parameter from the creation request. Controls the diversity of model output. Valid range: [0, 2). Returns the model default if not set.top_p floatEchoes the top_p parameter from the creation request. Nucleus sampling probability threshold. Valid range: (0, 1.0]. Returns the model default if not set.frequency_penalty floatEchoes the frequency_penalty parameter from the creation request. Positive values reduce the likelihood of repeated words.presence_penalty floatEchoes the presence_penalty parameter from the creation request. Positive values increase the likelihood of introducing new topics.top_logprobs integerEchoes the top_logprobs parameter from the creation request. Number of most likely tokens returned at each position. 0 if not enabled.store booleanEchoes the store parameter from the creation request. true means the response is stored and can be referenced by previous_response_id. false means it is not stored.service_tier stringService tier. Always default.background booleanWhether the response was executed asynchronously. Model Studio currently supports synchronous calls only, so this is always false.metadata objectEchoes the metadata parameter from the creation request. Custom key-value pairs attached to the response. Empty object {} if not set.

{
    "background": false,
    "completed_at": 1778676420,
    "created_at": 1778676418,
    "frequency_penalty": 0.0,
    "id": "resp_801bc2c4-93d9-910f-b35d-5274f5a737c1",
    "metadata": {},
    "model": "qwen-plus",
    "object": "response",
    "output": [
        {
            "content": [
                {
                    "annotations": [],
                    "text": "Hello! Nice to meet you. How can I help you?",
                    "type": "output_text"
                }
            ],
            "id": "msg_8c54756c-9b65-4a95-81d7-4276d91406db",
            "role": "assistant",
            "status": "completed",
            "type": "message"
        }
    ],
    "parallel_tool_calls": true,
    "presence_penalty": 0.0,
    "service_tier": "default",
    "status": "completed",
    "store": true,
    "temperature": 1.0,
    "tool_choice": "auto",
    "tools": [],
    "top_logprobs": 0,
    "top_p": 1.0,
    "usage": {
        "input_tokens": 45,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens": 63,
        "output_tokens_details": {
            "reasoning_tokens": 0
        },
        "total_tokens": 108,
        "x_details": [
            {
                "input_tokens": 45,
                "output_tokens": 63,
                "prompt_tokens_details": {
                    "cached_tokens": 0
                },
                "total_tokens": 108,
                "x_billing_type": "response_api"
            }
        ]
    }
}

Error response

Returned when the specified Response ID does not exist:

{
    "error": {
        "message": "Response with id 'resp_xxx' not found.",
        "type": "InvalidParameter"
    }
}

Path parameters

Response

​Error response

Error response