All AI models · LLM benchmarks · Methodology

Meta

Prompt Guard 2 86M

Safety model for policy screening, moderation, and risk-aware routing workflows

Model facts

Context window
512 tokens
Maximum output
512 tokens
Cheapest paid input
$0.04 per 1M tokens
Cheapest paid output
$0.04 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

open weights, text.

Observed price history

  • 2026-08-24: $0.04 input / $0.04 output per 1M tokens

API providers

  • Groq — model id meta-llama/llama-prompt-guard-2-86m; $0.04 input / $0.04 output per 1M tokens; provider documentation