LLM Reference

ELYZA Japanese Llama 2 13B vs ShieldGemma 9B

ELYZA Japanese Llama 2 13B (2023) and ShieldGemma 9B (2024) are compact production models from ELYZA and Google DeepMind. ELYZA Japanese Llama 2 13B ships a not-yet-sourced 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 ELYZA Japanese Llama 2 13B when provider fit matters.

Decision scorecard

Local evidence first
SignalELYZA Japanese Llama 2 13BShieldGemma 9B
Best forgeneral production evaluationgeneral production evaluation
Decision fitGeneralClassification
Context window—8k
Cheapest output--
Provider routes0 tracked1 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose ELYZA Japanese Llama 2 13B when...
  • Use ELYZA Japanese Llama 2 13B when your own prompt tests beat the comparison signals; the local data does not show a decisive standalone advantage yet.
Choose ShieldGemma 9B when...
  • ShieldGemma 9B has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • ShieldGemma 9B has broader tracked provider coverage for fallback and route flexibility.
  • 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.

ELYZA Japanese Llama 2 13B

Unavailable

No complete token price in local provider data

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

ELYZA Japanese Llama 2 13B -> ShieldGemma 9B
  • No overlapping tracked provider route is sourced for ELYZA Japanese Llama 2 13B and ShieldGemma 9B; plan for SDK, billing, or endpoint changes.
ShieldGemma 9B -> ELYZA Japanese Llama 2 13B
  • No overlapping tracked provider route is sourced for ShieldGemma 9B and ELYZA Japanese Llama 2 13B; plan for SDK, billing, or endpoint changes.

Specs

Specification
Released2023-08-022024-07-01
Context window—8k
Parameters13B9B
ArchitectureDecoder OnlyDecoder Only
LicenseLlama 2 CommunityGemma
OpennessOpen weightsOpen weights
WeightsUnknownUnknown
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: conditional
Knowledge cutoff--

Pricing and availability

Pricing attributeELYZA Japanese Llama 2 13BShieldGemma 9B
Input price--
Output price--
Providers-

Pricing not yet sourced for either model.

Capabilities

CapabilityELYZA Japanese Llama 2 13BShieldGemma 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: 2026-05-19. Data sourced from public model cards and provider documentation.