Qwen2.5-VL-7B-Instruct
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: captionIdentifier for the type of task being performed.
taskUUID
stringrequiredUUID v4UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.
webhookURL
stringuriWebhook 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
- WebhooksPLATFORM
- Webhooks
deliveryMethod
stringdefault: syncDetermines how the API delivers task results.
Allowed values2 values
- Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.
Learn more1 resource
- Task PollingPLATFORM
includeCost
booleanInclude task cost in the response.
Inputs
Input resources for the task (images, audio, etc). These must be nested inside the inputs object.
inputs object.inputs»imageimage
stringrequiredImage input (UUID, URL, Data URI, or Base64).
Core Parameters
Primary parameters that define the task output.
model
stringrequiredvalue: alibaba-qwen2-5-vl-7b-instructSend
autoinstead 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
stringInstructions or questions to guide the image analysis.