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

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 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 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

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.