Llama Guard 2 8B

Released
2024-04-18
Last refreshed
2026-10-12
Status
Researched 28d ago
Open weightsCommercial use: conditionalClassification
AI at Meta releases · 11 in the last 12 monthsChangelog →
Specifications
Released
2024-04-18
Context
8K
Parameters
8B
Architecture
Decoder Only
Knowledge cutoff
2023-03
Specialization
safety
Openness
Open weights
License
Llama 2 CommunityCommercial use: conditional
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by
AI at Meta

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website
Pricing
Output / 1M
$0.200
Input / 1M
$0.200

Cheapest of 2 routes · Fireworks AI

Providers(2)
Fireworks AIReplicate API
View 2 provider routes

About

Llama Guard 2 is an 8B-parameter LLM built on the Llama 3 architecture, specifically designed for content moderation tasks. Released by Meta on April 18, 2024, it excels in classifying both inputs and outputs of LLMs across 11 safety categories. The model generates text outputs indicating whether content is safe or unsafe, providing detailed feedback on violations. It aims to enhance user experience by minimizing false positives while maintaining high accuracy in content moderation, supporting developers in creating safer AI applications .

Providers(2)

Compare all 2

Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Fireworks AI$0.200$0.200
Provisioned
Replicate API$0.050$0.250
Serverless

Deprecated provider routes(1)

ProviderStatusCatalog ID
OctoAI API (Deprecated)Deprecated—

Available via routers & gateways(1)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Classification

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

Compare Llama Guard 2 8B with other models

Show all 34 popular comparisonssorted by 7-day search impressions
Llama Guard 2 8B vs Llama 3 Swallow 70B Instruct3Llama Guard 2 8B vs GPT-23Llama Guard 2 8B vs Mistral Large 3 675B Instruct3Llama Guard 2 8B vs Together AI - Llama 3 8B Lite3Llama Guard 2 8B vs Together AI - Gemma 3n-e4B3Llama Guard 2 8B vs Mistral Large 23Llama Guard 2 8B vs Mistral Nemotron3Llama Guard 2 8B vs Phi-4 Mini Flash Reasoning3Llama Guard 2 8B vs Llama 3.1 Nemotron Nano VL 8B v12Llama Guard 2 8B vs Bielik 11B v2.6 Instruct2Llama Guard 2 8B vs Falcon 3 7B Instruct2Llama Guard 2 8B vs Claude Instant 1.12Llama Guard 2 8B vs Mistral 7B v0.12Llama Guard 2 8B vs GPT-4 Turbo Preview2Llama Guard 2 8B vs Magistral Small 25062Llama Guard 2 8B vs Llama 3.1 Swallow 8B Instruct1Llama Guard 2 8B vs Codex 11Llama Guard 2 8B vs Llama 3.1 Nemotron Nano 4B v1.11Llama Guard 2 8B vs Stockmark 2 100B Instruct1Llama Guard 2 8B vs Marin 8B Instruct1Llama Guard 2 8B vs Llama 3 Taiwan 70B Instruct1Llama Guard 2 8B vs Gemma 2 9B SahabatAI Instruct1Llama Guard 2 8B vs Mistral Medium 3 Instruct1Llama Guard 2 8B vs Codex Mini Latest1Llama Guard 2 8B vs Dracarys Llama 3.1 70B Instruct1Llama Guard 2 8B vs Claude Instant1Llama Guard 2 8B vs Llama 2 7B Chat1Llama Guard 2 8B vs MiniCPM 2B1Llama Guard 2 8B vs Aquila 2 34B1Llama Guard 2 8B vs ELYZA Japanese Llama 2 7B1Llama Guard 2 8B vs GPT-11Llama Guard 2 8B vs GPT-2 Medium1Llama Guard 2 8B vs Italia 10B Instruct1Llama Guard 2 8B vs Qwen2-7B-Instruct1