xpu liveBETA
Models›Llama Guard 3 8B

Llama Guard 3 8B

Model reference ↗

Model ranking

Not matched to the current verified ranking snapshot.

Pricing 1 Model information

Provider prices 1

Lowest input price per billing unit. Conditions in Details.

ProviderPriceProvider model IDStatusContext / max outputSource
Cloudflare Workers AIllama-guard-3-8b
Standard
Input $0.484USD / 1M tokensOutput $0.03USD / 1M tokens
Updated 2026-11-22 · 15:43 UTC
@cf/meta/llama-guard-3-8bCatalog-listed
Conditions

Public catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine.

Context tokens 131072Official source ↗2026-10-20

Llama Guard 3 8B is Meta’s safety classification model for evaluating text against a documented risk taxonomy. It serves a different purpose from a general conversational Llama checkpoint.

Llama Guard 3 8B: suitable applications

Use it as one signal in content moderation and in evaluating prompts or responses before applying an application’s own policy.

Capabilities and technical details

The model supplies a task-specific safety interface and category-oriented outputs that can be integrated into a broader moderation pipeline.

Llama Guard 3 8B accepts text and returns text. The recorded input reference is 131,072 tokens, with any lower Cloudflare cap recorded separately. The recorded terms are Llama 3.1 Community License; the linked source explains their scope.

Llama Guard 3 8B limitations and selection

Safety labels are not a complete policy decision. False positives, missed risks and domain-dependent behavior require application-level handling.

Map the model’s categories to your actual policy and evaluate both benign edge cases and adversarial inputs; do not rely on one score as a universal safety guarantee.

Llama Guard 3 8B API pricing

Llama Guard 3 8B pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.

Review the Cloudflare Llama Guard 3 8B endpoint reference and the Meta model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.

CONTEXT TOKENS131,072Source not recorded
MAX OUTPUT TOKENSNot suppliedProvider-dependent
PROVIDERS1Linked in this catalog
SOURCE CHECKED2026-10-20Sources reviewed; unknown fields labeled

Specifications

Catalog model ID
meta/llama-guard-3-8b
Developer model ID / revision
Not verified in cited sources
Context / input token limit
131,072Cloudflare Workers AI input cap ↗
Maximum output tokens
Not verified in cited sources
Tool calling
Not verified in cited sources
Structured output
Not verified in cited sources
API parameters (source-specific)
Not verified in cited sources
Weight license / access terms
Llama 3.1 Community LicenseDeveloper weight license / hosted access terms ↗
Total parameters (billions)
8Developer model card / documentation ↗
Active parameters (billions)
Not verified in cited sources
Parameter-count details
Developer-declared nominal model size; serialized tensor counts can differ. Active parameters, when supplied, are separate from total parameters.Developer model card ↗
Download size (GB)
Depends on checkpoint and precision; no verified file size
Release date
Not verified in cited sources
Notes
Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Context shown here is the explicitly documented Cloudflare input cap; a separate publisher maximum is not verified. Parameter sizes are developer-declared nominal labels; serialized tensor counts may differ.

Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.