LLaVA-1.6-Mistral-7B

January 31, 2024

LLaVA-1.6-Mistral-7B is a multimodal vision-language model that processes images alongside text to generate descriptive and reasoning-based responses. It enables image captioning and visual understanding by combining a vision encoder with a Mistral 7B language backbone.

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

Specifies a webhook URL where JSON responses will be sent 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.

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: meta-llava-1-6-mistral-7b

Identifier of the model to use for generation.

Learn more3 resources

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