ReplicateContent moderationComing soon

meta/llama-guard-4-12b

Name: meta/llama-guard-4-12b
Brand: Replicate

meta/llama-guard-4-12b is a content moderation tool from Replicate that runs in the background and returns structured JSON. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

Up to $0.000143 per run at the default inputs. The final charge comes from usage.

Limits

Runs: In the background
Returns: json
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	The prompt to send to the model. Do not use if using messages.
`system_prompt` required	text	—	System prompt to set the assistant's behavior
`top_p`	number 0 to 1	1	Nucleus sampling parameter - the model considers the results of the tokens with top_p probability mass. (0.1 means only the tokens comprising the top 10% probability mass are considered.)
`image_input`	list	[]	List of images to send to the model
`temperature`	number 0 to 2	1	Sampling temperature between 0 and 2
`presence_penalty`	number -2 to 2	0	Presence penalty parameter - positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
`frequency_penalty`	number -2 to 2	0	Frequency penalty parameter - positive values penalize the repetition of tokens.
`max_completion_tokens`	number (whole) 1 to 1024	512	Maximum number of completion tokens to generate

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "meta/llama-guard-4-12b",
    "input": {
      "prompt": "<prompt>",
      "system_prompt": "<system_prompt>"
    }
  }'