Error messages

This topic describes the error codes and their corresponding messages that you may encounter when using Alibaba Cloud Model Studio.

HTTP status code	Code	Message	Description
-	-	error.AuthenticationError: No api key provided. You can set by dashscope.api_key = your_api_key in code, or you can set it via environment variable DASHSCOPE_API_KEY= your_api_key.	The API key is not provided when using the DashScope SDK. Set your API key as an environment variable.
-	-	openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable	The API key is not provided. You can set the API key as an environment variable, or write the API key in the code (not recommended).
-	mismatched_model	The model 'xxx' for this request does not match the rest of the batch. Each batch must contain requests for a single model.	In a batch task, all requests must use the same model. Check your input file according to the input format.
-	duplicate_custom_id	The custom_id 'xxx' for this request is a duplicate of another request. The custom_id parameter must be unique for each request in a batch.	In a batch task, each request ID must be unique. Check your input file according to the input format and ensure all request IDs are not duplicated.
-	model_not_found	"The provided model 'xxx' is not supported by the Batch API.	The current model does not support batch calls, or the model name is incorrect. Check the supported models and the spelling of their name.
400	invalid_parameter_error	current user api does not support http call	The open source Qwen3 models do not support non-streaming output, using Stream instead.
400	invalid_parameter_error	This model only support stream mode, please enable the stream parameter to access the model.	The model only supports streaming output.
400	InvalidParameter	Required parameter(s) missing or invalid, please check the request parameters.	The request parameters are invalid.
400	APIConnectionError	Connection error.	Local network issue. This is usually because of an enabled proxy. Disable or restart the proxy and try again.
400	InvalidParameter	Temperature should be in [0.0, 2.0)	The temperature parameter is not within the range of [0.0, 2.0). For the parameter range, see Qwen.
400	invalid_request_error	'temperature' must be Float	The temperature parameter is not within the range of [0.0, 2.0). For the parameter range, see Qwen.
400	InvalidParameter	Range of top_p should be (0.0, 1.0]	The top_p parameter is not within the range of (0.0, 1.0]. For the parameter range, see Text generation - Qwen.
400	invalid_request_error	'top_p' must be Float	The top_p parameter is not within the range of (0.0, 1.0]. For the parameter range, see Text generation - Qwen.
400	InvalidParameter	Presence_penalty should be in [-2.0, 2.0]	The presence_penalty parameter is not within the range of [-2.0, 2.0]. For the parameter range, see Text generation - Qwen.
400	InvalidParameter	Range of max_tokens should be [1, 2000]	The max_tokens parameter is not within the range of [1, Maximum output of the model]. For the output limits of models, see Models.
400	InvalidParameter	Range of n should be [1, 4]	The n parameter is not within the range of [1, 4]. For the parameter range, see Text generation - Qwen.
400	InvalidParameter	Range of seed should be [0, 9223372036854775807]	When calling LLM API using the DashScope method, the seed parameter is not within the range of [0, 9223372036854775807]. For the parameter range, see Text generation - Qwen.
400	invalid_request_error	-1 is lesser than the minimum of 0 - 'seed' or 'seed' must be Integer	When calling LLM API using the OpenAI method, the seed parameter is not within the range of [0, 2³¹-1]. For the parameter range, see Text generation - Qwen.
400	InvalidParameter	The "stop" parameter must be of type "str", "list[str]", "list[int]", or "list[list[int]]", and all elements within the list must be of the same type.	The stop parameter does not conform to the "str", "list[str]", "list[int]", or "list[list[int]]" formats. For parameter descriptions, see Text generation - Qwen.
400	InvalidParameter	Parameter top_k be greater than or equal to 0	The top_k parameter cannot be negative. For the parameter range, see Text generation - Qwen.
400	InvalidParameter	Repetition_penalty should be greater than 0.0	The repetition_penalty parameter cannot be negative. For the parameter range, see Text generation - Qwen.
400	InvalidParameter	Value error, batch size is invalid, it should not be larger than xx.	When calling a embedding model, the number of input rows exceeds the upper limit. For row limits, see Embedding.
400	InvalidParameter	Range of input length should be [1, xxxx]	The input length exceeds the upper limit. For the limits, see Models.
400	InvalidParameter	The provided URL does not appear to be valid. Ensure it is correctly formatted.	When using visual understanding and omni-modal models, the URL of the input data is invalid. The URL must start with http://, https://, data:, or file://. If it starts with `data:`, the Base64 encoded data must include `"base64"` before the data, otherwise an error will occur.
400	InvalidParameter	Input should be a valid dictionary or instance of GPT3Message	The format of the messages field does not meet the requirements, such as mismatched parentheses or missing necessary key-value pairs.
400	invalid_request_error	'audio' output only support with stream=true	When using Qwen-Omni, stream is not enabled.
400	InvalidParameter	Either "prompt" or "messages" must exist and cannot both be none	The prompt and messages fields cannot both be empty. The cause might be a format error. For example, when calling a model using the DashScope SDK, messages must be placed in the input object instead of being parallel to the model parameter. `{ "model": "specified model", "input": { "messages": [ {"role": "user", "content": "Who are you"}, ] }, "parameters": { "result_format": "message" } }`
400	InvalidParameter	'messages' must contain the word 'json' in some form, to use 'response_format' of type 'json_object'.	When enabling structured output, the System Message or User Message does not guide the model to output in JSON format. Example: "Please output in JSON format."
400	InvalidParameter	Too many files provided.	The number of provided file IDs exceeds the limit. Provide no more than 100 file IDs.
400	InvalidParameter	File [id:file-fe-***********] exceeds size limit.	The size of the provided file exceeds the limit. Make sure that the file is smaller than 150 MB.
400	InvalidParameter	File [id:file-fe-***********] exceeds page limits (15000 pages).	The number of pages in the provided file exceeds the limit. Make sure that the number of pages is less than 15,000.
400	InvalidParameter	File [id:file-fe-***********] content blank.	The provided file is empty. Make sure that the file content meets the requirements.
400	InvalidParameter	Total message token length exceed model limit (10000000 tokens).	The total input exceeds 10,000,000 tokens. Make sure that the message length meets the requirements.
400	DataInspectionFailed data_inspection_failed	Input or output data may contain inappropriate content. Input data may contain inappropriate content. Output data may contain inappropriate content.	Data inspection error. The input or output may contain inappropriate content and is blocked during content moderation.
400	BadRequest.EmptyInput	Required input parameter missing from request.	The input cannot be empty.
400	BadRequest.EmptyParameters	Required parameter "parameters" missing from request.	The parameters parameter cannot be empty.
400	BadRequest.EmptyModel	Required parameter "model" missing from request.	The model parameter cannot be empty.
400	InvalidURL	Invalid URL provided in your request.	The request URL is incorrect.
400	InvalidParameter	The video modality input does not meet the requirements because: the range of sequence images shoule be (4, 80)/(4,512).	When using the Qwen-VL model for video understanding and passing in as an image list, the number of images does not meet the requirements. For details, see Visual understanding. Qwen2.5-VL series models: At least 4 images and at most 512 images Other models: At least 4 images and at most 80 images
400	InvalidParameter	Exceeded limit on max bytes per data-uri item : 10485760'.	When using the OpenAI SDK to pass local image or video to Qwen-VL, QVQ, or Qwen-Omni, the image or video size does not meet the requirements. Input local file: The Base64-encoded video or image is less than 10 MB. Input file URL: For image: The size of an individual file should not exceed 10 MB. For video: The Qwen2.5-VL series models support video files up to 1 GB. Other models support video files up to 150 MB.
400	InvalidParameter	The image length and width do not meet the model restrictions. [absolute aspect ratio must be smaller than 200, got n / m]. The image length and width do not meet the model restrictions. [height:n or width:m must be larger than 10].	The length and width of the image passed into Qwen-VL do not meet the requirements: The width and height of the image must not be less than 10 pixels. The aspect ratio must not exceed 200:1 or 1:200.
400	InvalidParameter	The file format is illegal and cannot be opened.	The image file format is invalid and cannot be opened. Qwen-VL supports the following image formats: BMP, DIB, ICNS, ICO, JPEG, JPEG2000, PNG, SGI, TIFF, WEBP.
400	InvalidParameter	Failed to download multimodal content. Download the media resource timed out during the data inspection process.	Failed to download the multimodal files or download timed out. Possible causes: Network reasons. Check your network connectivity. The URL of the file is an OSS internal URL. Because the OSS internal network is not connected to Model Studio, do not use the internal URL.
400	InvalidParameter	Don't have authorization to access the media resource during the data inspection process.	Not authorized to access the media file. Possible cause: When calling the model, you passed a signed file URL from OSS and the URL has expired. Make sure you access the file within the validity period of the URL.
400	invalid_value	Invalid value: vide. Supported values are: 'text','image_url','video_url' and 'video'.	When calling the model using the OpenAI SDK, the value of the type attribute of the content parameter is invalid. Valid values: text, image_url, video, or video_url.
400	InvalidParameter	Invalid video file.	The video file provided is invalid.
400	InvalidParameter	The video modality input does not meet the requirements because: The video file is too long.	The video duration exceeds the limit of Qwen-VL or Qwen-Omni: Qwen2.5-VL supports videos between 2 seconds and 10 minutes. Other Qwen-VL or Qwen-Omni models support videos between 2 seconds and 40 seconds.
400	Arrearage	Access denied, please make sure your account is in good standing.	Possible cause 1: Your Alibaba Cloud account has overdue payment. Go to Expenses and Costs to confirm or recharge There may be a slight delay in the model's response regarding account balance. Wait a few minutes and try again. Possible cause 2: The batch interface returns this error because you have not activated Model Studio. Go to Models to activate Model Studio for free, and then get an API key for the call.
400	UnsupportedOperation	The operation is unsupported on the referee object.	The referee object does not support this operation. This message may vary based on the actual scenario.
400	InvalidSchema	Database schema is invalid for text2sql.	Enter the schema of your database.
400	InvalidSchemaFormat	Database schema format is invalid for text2sql.	The schema format of the input data table is invalid.
400	FaqRuleBlocked	Input or output data is blocked by faq rule.	The input or output is blocked by FAQ rules.
400	CustomRoleBlocked	Input or output data may contain inappropriate content with custom rule.	The input or output is blocked by custom rules.
400	InternalError.Algo	Missing Content-Length of multimodal url.	The response header of the URL request lacks `Content-Length`. If the issue persist, try using another image URL. Check `Content-Length` Open your browser (such as Chrome or Firefox). Open the developer tools (usually by pressing F12 or right-click and select Inspect). Go to the Network tab. Enter the image URL into the address bar and access it. Find the corresponding request and look for the Content-Length field in the Response Headers section.
400	InvalidParameter	Wrong Content-Type of multimodal url	The `Content-Type` field of the response header information of the URL request is incorrect. If the issue cannot be resolved, try using another image link. The Qwen-VL model supports the following Content Types: image/bmp, image/bmp, image/icns, image/x-icon, image/jpeg, image/jp2, image/png, image/sgi, image/tiff, image/webp. For details, see Supported image formats. Check `Content-Type` Open your browser (such as Chrome or Firefox). Open the developer tools (usually by pressing F12 or right-click and select Inspect). Go to the Network tab. Enter the image URL into the address bar and access it. Find the corresponding request and look for the Content-Type field in the Response Headers section.
400	InvalidParameter	The content field is a required field.	The content parameter is not configured when calling the model using the Java SDK.
400	invalid_request_error	Payload Too Large.	When executing a batch task, the size of the uploaded JSONL file exceeds the upper limit. To upload the file, check and ensure that the file size meets the limit, or consider splitting the file into multiple smaller files. For the JSONL file format, see Input file format.
401	InvalidApiKey invalid_api_key	Invalid API-key provided. Incorrect API key provided.	Possible cause 1: The API Key in the request is incorrect. Obtain a new API Key. Possible cause 2: The dashscope.base_http_api_url or base_url in the request is incorrect. Check the domain name in the URL and make sure it is `dashscope-intl.aliyuncs.com`.
403	AccessDenied access_denied	Access denied.	You are not authorized to access this API. For example, you are not in the invitational preview. Go to the Model Studio console and under the corresponding model card in Models, click Apply Now.
403	Workspace.AccessDenied	Workspace access denied.	You are not authorized to access the applications or models in this workspace. If you call the models in the sub-workspace, see Call a model in a sub-workspace. You can also use the API key of the Alibaba Cloud account, which has permissions for all workspaces.
403	Model.AccessDenied	Model access denied.	The RAM user is not authorized to access models in this workspace. Perform the following steps: Check whether you have specified the ID of the sub-workspace. RAM users cannot access applications or models in the default workspace. Check whether the RAM user is authorized to access the sub-workspace. Check whether the sub-workspace is authorized to call the model. For more information, see Call a model in a sub-workspace.
403	AccessDenied.Unpurchased	Access to model denied. Please make sure you are eligible for using the model.	You may not have activated the Model Studio service: You need to register or log on to your Alibaba Cloud account, and then go to Models to activate Model Studio.
404	WorkSpaceNotFound	WorkSpace can not be found.	The workspace that you specify does not exist.
404	ModelNotFound model_not_found	Model can not be found. The model xx does not exist.	The model that you specify does not exist.
404	ModelNotFound model_not_found	The model xx does not exist or you do not have access to it.	You have not activated Model Studio yet. You need to go to Model Market to activate the model service.
408	RequestTimeOut	Request timed out, please try again later. Response timeout! I/O error on POST request for "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions": timeout	The request timed out. You can try to initiate the request again. The request may time out because the response is too long. You can try the streaming output mode when making requests..
413	BadRequest.TooLarge	Payload Too Large.	The gateway at the access layer returns an error that the request body is too large. If the error is returned by the Microservice Engine (MSE) gateway, no code is returned and the message cannot be customized. If the error is returned by the RESTful gateway, a code is returned.
415	BadRequest.InputDownloadFailed	Failed to download the input file: xxx.	Failed to download the input file, which may be due to download timeout, download failure, or file size exceeding the limit. The message may include additional details.
415	BadRequest.UnsupportedFileFormat	The format of the input file is not supported.	The format of the input file is not supported.
429	Throttling	Requests throttling triggered.	The API request triggers throttling.
429	Throttling.RateQuota	Requests rate limit exceeded, please try again later.	The frequency of calls triggers throttling threshold, such as the number of requests per second. We recommend waiting for a period of time before trying to call again.
429	Throttling.AllocationQuota insufficient_quota	Allocated quota exceeded, please increase your quota limit. You exceeded your current quota, please check your plan and billing details.	The number of requests triggers throttling, such as the number of tokens generated per minute.
429	LimitRequests limit_requests	You exceeded your current requests list	You exceed the throttling threshold. You can make requests again after falling down below the throttling threshold.
429	Throttling.AllocationQuota	Free allocated quota exceeded.	The free quota has expired or been exhausted, and the model does not support paid access.
429	PrepaidBillOverdue	The prepaid bill is overdue.	Subscription of this workspace is overdue.
429	PostpaidBillOverdue	The postpaid bill is overdue.	The model inference service is overdue.
429	CommodityNotPurchased	Commodity has not purchased yet.	The service is not activated in this workspace.
500	InternalError internal_error	An internal error has occured, please try again later or contact service support.	An internal error occurred. If you are using the Qwen-Omni, you need to use streaming output mode.
500	InternalError.Algo	An internal error has occured during execution, please try again later or contact service support.	An internal algorithm error occurred.
500	InternalError.Algo	Role must be in [user, assistant]	When using the Qwen-MT model, ensure that the messages array contains only one element, which must be a User Message.
500	SystemError system_error	An system error has occured, please try again later.	A system error occurred.
500	InternalError.Timeout	An internal timeout error has occured during execution, please try again later or contact service support.	The asynchronous task waits for 3 hours after being submitted from the gateway to the algorithm service layer. If no result is returned, the task times out.
500	RewriteFailed	Failed to rewrite content for prompt.	Prompt rewriting failed.
500	RetrivalFailed	Failed to retrieve data from documents.	Document retrieval failed.
500	AppProcessFailed	Failed to proceed application request.	Application flow processing failed.
500	ModelServiceFailed	Failed to request model service.	Model call failed.
500	InvokePluginFailed	Failed to invoke plugin.	Plug-in call failed.
503	ModelUnavailable	Model is unavailable, please try again later.	The model is temporarily unavailable for service.
503	ModelServingError	Too many requests. Your requests are being throttled due to system capacity limits. Please try again later.	Our network resources are currently saturated and cannot process your request at this time. You can try again later.
	NetworkError network_error	Can not find api-key.	The environment variable configuration is not effective. You can restart the client or IDE and try again. For more information, see FAQ.

Response parameters

In case of errors, an HTTP status code and a message that contains the details are returned. Sample response:

{
  	"request_id": "54dc32fd-968b-4aed-b6a8-ae63d6fda4d5",
  	"code": "InvalidApiKey",
  	"message": "The API key in your request is invalid."
}

Parameters description

Parameters	Type	Description
HTTP status code	integer	The status code 200 indicates that the request is successful. Other status codes indicate that the request failed.
request_id	string	The request ID. You can identify a call based on the request_id parameter during troubleshooting.
code	string	The error code returned in case of failure, see the Code column of the preceding table.
message	string	The message returned in case of failure, see the Message column of the preceding table. Take note that the message may vary based on the actual scenario and may contain more specific information that is different from the preceding table.