LLM Reference

Llama Guard 2 8B vs ShieldGemma 9B

Llama Guard 2 8B (2024) and ShieldGemma 9B (2024) are compact production models from AI at Meta and Google DeepMind. Llama Guard 2 8B ships a 8k-token context window, while ShieldGemma 9B ships a 8k-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads. It focuses on practical selection signals rather than broad model-family marketing.

ShieldGemma 9B is safer overall; choose Llama Guard 2 8B when provider fit matters.

Decision scorecard

Local evidence first
SignalLlama Guard 2 8BShieldGemma 9B
Best forprovider-routed productiongeneral production evaluation
Decision fitClassificationClassification
Context window8k8k
Cheapest output$0.25/1M tokens-
Provider routes3 tracked1 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose Llama Guard 2 8B when...
  • Llama Guard 2 8B has broader tracked provider coverage for fallback and route flexibility.
  • Local decision data tags Llama Guard 2 8B for Classification.
Choose ShieldGemma 9B when...
  • Local decision data tags ShieldGemma 9B for Classification.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Llama Guard 2 8B

$103

Cheapest tracked route/tier: Replicate API

ShieldGemma 9B

Unavailable

No complete token price in local provider data

Cost delta unavailable until both models have sourced input and output token prices.

Switch friction

Llama Guard 2 8B -> ShieldGemma 9B
  • No overlapping tracked provider route is sourced for Llama Guard 2 8B and ShieldGemma 9B; plan for SDK, billing, or endpoint changes.
ShieldGemma 9B -> Llama Guard 2 8B
  • No overlapping tracked provider route is sourced for ShieldGemma 9B and Llama Guard 2 8B; plan for SDK, billing, or endpoint changes.

Specs

Specification
Released2024-04-182024-07-01
Context window8k8k
Parameters8B9B
ArchitectureDecoder OnlyDecoder Only
LicenseLlama 2 CommunityGemma
OpennessOpen weightsOpen weights
WeightsAvailableUnknown
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: conditional
Knowledge cutoff2023-03-

Pricing and availability

Pricing attributeLlama Guard 2 8BShieldGemma 9B
Input price$0.05/1M tokens-
Output price$0.25/1M tokens-
Providers

Capabilities

CapabilityLlama Guard 2 8BShieldGemma 9B
VisionNoNo
MultimodalNoNo
ReasoningNoNo
JSON / Tool useNoNo
Structured outputsNoNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Continue comparing

Last reviewed: 2026-07-11. Data sourced from public model cards and provider documentation.