Skip to content
ArenaPlatform

meta-llama/llama-prompt-guard-2-86m

groq/llama-prompt-guard-2-86m

The larger Prompt Guard 2 classifier from Meta (April 2025), built on multilingual mDeBERTa-v3 to flag prompt-injection and jailbreak text across languages; Meta reports 97.5% English recall at a 1% false-positive rate. Inputs over 512 tokens must be split.

Get API KeyRead the Docs
API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "groq/llama-prompt-guard-2-86m",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read docs
Input Price
$0.034 / 1M tokens
Output Price
$0.034 / 1M tokens
Context
512 tokens
Output
Text

Capabilities

Explore what meta-llama/llama-prompt-guard-2-86m supports, then use the API section for a request tailored to this model.

Max tokens

Model Information

Provider
Groq
Product
Language Models
Release Date
Apr 29, 2025
Model Max Output
512 tokens
Data Policy
Not specified
Region
Global
Input
Text
Output
Text
Provider Documentation

Playground

Try meta-llama/llama-prompt-guard-2-86m by Groq. Requests use the selected workspace’s credits and API pricing.

meta-llama/llama-prompt-guard-2-86mCredits —
meta-llama/llama-prompt-guard-2-86m
⌘ / Ctrl + Enter to send
Sign in to run a requestAPI reference

Providers

Compare available endpoints, pricing, and context limits for meta-llama/llama-prompt-guard-2-86m.

ProviderContextOutputInput PriceOutput PriceEndpoint
Groq512 tokensText$0.034 / 1M tokens$0.034 / 1M tokens
meta-llama/llama-prompt-guard-2-86m

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Model-specific limits are available in the provider documentation .

Provider Notes

General LLM inference is an integration preview. Managed billing and deployment acceptance must be enabled before requests can be served.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "groq/llama-prompt-guard-2-86m",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read docs
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelgroq/llama-prompt-guard-2-86m — Required model identifier.
max_tokensView Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Model-specific limits are available in the provider documentation .

Similar Models

Explore more language models and compare their capabilities.

ModelContextInput PriceOutput Price
openai/gpt-oss-safeguard-20bGroq131.1K tokens$0.0638 / 1M tokens$0.255 / 1M tokens
meta-llama/llama-prompt-guard-2-22mGroq512 tokens$0.0255 / 1M tokens$0.0255 / 1M tokens
Claude Haiku 5.5Anthropic1M tokens$0.085 / 1M tokens$0.425 / 1M tokens
GPT-6.1 SolOpenAI1.1M tokens$1.70 / 1M tokens$8.50 / 1M tokens
Claude Sonnet 5.5Anthropic1M tokens$1.70 / 1M tokens$8.50 / 1M tokens
Claude Opus 5.5Anthropic1M tokens$3.40 / 1M tokens$17.00 / 1M tokens
View All Language Models