Blocks

Vision

Analyze images with vision models

Process visual content with customizable prompts to extract insights and information from images.

Back to Catalog
Toolsvision

Block Preview

Vision

Analyze images with vision models

Usage

  1. Add the block to your workflow and connect it to the upstream step.
  2. Configure any required credentials or tokens in the inputs.
  3. Fill in required inputs and optional parameters for the run.
  4. Run a test execution, inspect outputs, and iterate before deploying.
  5. Deploy the vision block with monitoring enabled in production.

Inputs (UI)

Image URL

short-input

Placeholder: Enter publicly accessible image URL

Layout: full

Vision Model

dropdown

Layout: half

Options: gpt-4o, claude-3-opus-20240229, claude-3-sonnet-20240229

Prompt

long-input

Placeholder: Enter prompt for image analysis

Layout: full

API Key

short-input

Placeholder: Enter your API key

Layout: full

Inputs (API)

apiKey

string

Required

imageUrl

string

Required

model

string

Optional

prompt

string

Optional

Outputs

Primary response type:

{
  "content": "string",
  "model": "string",
  "tokens": "number"
}

Tool Access

vision_tool
Vision | NowFlow Blocks