All models

Llama Guard 4

Screen text or an image against Meta's hazard taxonomy

Languagev1.0.03 inputsBOOLEANTEXT

How do I keep my sourdough starter alive over winter?

true

Screened against Meta's hazard taxonomy — verdict: safe

Try it right here

Fill the inputs the node publishes and run it on your own account. The same ports, defaults and types the studio uses.

Inputs

TEXT
Content to screen
IMAGE
Image to screen
TEXT
Sign in to run

Running a model executes it on your account. Browsing the catalog stays free and needs no account.

Output

Fill in the inputs and run the node to see its output here.

Call it from your code

The same node, called by id from any surface. Every tab pins this node and passes the ports below.

import { BlitClient } from "@blitflow/sdk";

const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN });

const { outputs } = await runNode("llama-guard-4", {
  content: { value: "example" },
  image: { ref: "https://..." },
  policy: { value: "You are a content safety classifier." },
});

Schema

Every port this node publishes, with its type, its hint and the default it runs with. llama-guard-4 is the id you call.

Inputs

content*TEXT
Content to screen
imageIMAGE
Image to screen
policyTEXTYou are a content safety classifier.

Outputs

safeBOOLEAN
categoriesTEXT

Chain it with the rest of the catalog

Open the studio