Capability profile / Multimodal
Vision that fits your workflow.
Bring visual context into applications that work with images, documents, and interfaces.
Start with the right question.
Describe what an image-aware assistant should extract from a product screenshot.
Use in playgroundBuilt around your requirements
Choose a model with the capabilities your application requires. Evaluate the response format, context needs, and cost before integrating it into your workflow.
Provider connectionNot configured
Context and pricingDepends on selected model
Request preparationAvailable in playground