Qwen2.5-VL-7B-Instruct

by August 24, 2023

Qwen2.5-VL-7B-Instruct is a multimodal model that processes images and text together to perform visual reasoning, captioning, question answering, and structured output generation. It integrates a vision encoder with a 7B instruction-tuned language backbone to support rich interactive multimodal understanding.

API Options

Platform-level options for task execution and delivery.

taskType stringrequiredvalue: caption: Identifier for the type of task being performed.

taskUUID stringrequiredUUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

webhookURL stringuri

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more1 resource

Webhooks
PLATFORM

deliveryMethod stringdefault: sync

Determines how the API delivers task results.

Allowed values2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more1 resource

Task Polling
PLATFORM

includeCost boolean: Include task cost in the response.

routing object

Model router options. Only read when model is auto, and never sent to the model.

Properties3 properties

routing » preferences preferences object

Relative importance of each dimension when models are compared. Weights, not thresholds.

Properties3 properties

routing » preferences » quality quality integermin: 0max: 5: Importance of one dimension. 0 leaves it out of the decision.

routing » preferences » speed speed integermin: 0max: 5: Importance of one dimension. 0 leaves it out of the decision.

routing » preferences » cost cost integermin: 0max: 5: Importance of one dimension. 0 leaves it out of the decision.

routing » maxPrice maxPrice floatmin: 0: Upper bound on what this request may cost, in USD. A model whose cost cannot be bounded is not chosen.

routing » requirements requirements stringmax: 3000: Conditions the result has to meet, in plain words. A model that cannot meet them is not chosen.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » image image stringrequired: Image input (UUID, URL, Data URI, or Base64).

Core Parameters

Primary parameters that define the task output.

model stringrequiredvalue: alibaba-qwen2-5-vl-7b-instruct

Send auto instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See Model Router.

Learn more3 resources

prompt string: Instructions or questions to guide the image analysis.