Llama Prompt Guard 2 22M vs ShieldGemma 9B
Llama Prompt Guard 2 22M (2025) and ShieldGemma 9B (2024) are compact production models from AI at Meta and Google DeepMind. Llama Prompt Guard 2 22M ships a 512-token context window, while ShieldGemma 9B ships a 8K-token context window. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit. It focuses on practical selection signals rather than broad model-family marketing.
ShieldGemma 9B fits 16x more tokens; pick it for long-context work and Llama Prompt Guard 2 22M for tighter calls.
Decision scorecard
Local evidence first| Signal | Llama Prompt Guard 2 22M | ShieldGemma 9B |
|---|---|---|
| Decision fit | Classification and JSON / Tool use | Classification |
| Context window | 512 | 8K |
| Cheapest output | $0.03/1M tokens | - |
| Provider routes | 1 tracked | 1 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Llama Prompt Guard 2 22M uniquely exposes Structured outputs in local model data.
- Local decision data tags Llama Prompt Guard 2 22M for Classification and JSON / Tool use.
- ShieldGemma 9B has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Local decision data tags ShieldGemma 9B for Classification.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output prices on this page.
Llama Prompt Guard 2 22M
$31.50
Cheapest tracked route: GroqCloud
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
- No overlapping tracked provider route is sourced for Llama Prompt Guard 2 22M and ShieldGemma 9B; plan for SDK, billing, or endpoint changes.
- Check replacement coverage for Structured outputs before moving production traffic.
- No overlapping tracked provider route is sourced for ShieldGemma 9B and Llama Prompt Guard 2 22M; plan for SDK, billing, or endpoint changes.
- Llama Prompt Guard 2 22M adds Structured outputs in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-04-29 | 2024-07-01 |
| Context window | 512 | 8K |
| Parameters | 22M | 9B |
| Architecture | decoder only | decoder only |
| License | Llama 3.1 Community | 1 |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Llama Prompt Guard 2 22M | ShieldGemma 9B |
|---|---|---|
| Input price | $0.03/1M tokens | - |
| Output price | $0.03/1M tokens | - |
| Providers |
Capabilities
| Capability | Llama Prompt Guard 2 22M | ShieldGemma 9B |
|---|---|---|
| Vision | No | No |
| Multimodal | No | No |
| Reasoning | No | No |
| Function calling | No | No |
| Tool use | No | No |
| Structured outputs | Yes | No |
| Code execution | No | No |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on structured outputs: Llama Prompt Guard 2 22M. Both models share the core language-model surface, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
Pricing coverage is uneven: Llama Prompt Guard 2 22M has $0.03/1M input tokens and ShieldGemma 9B has no token price sourced yet. Provider availability is 1 tracked routes versus 1. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.
Choose Llama Prompt Guard 2 22M when provider fit are central to the workload. Choose ShieldGemma 9B when long-context analysis and larger context windows are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions. It also helps separate model capability from provider packaging, which can change cost and latency. For teams standardizing a stack, that distinction is often the difference between a benchmark win and a reliable deployment.
FAQ
Which has a larger context window, Llama Prompt Guard 2 22M or ShieldGemma 9B?
ShieldGemma 9B supports 8K tokens, while Llama Prompt Guard 2 22M supports 512 tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Is Llama Prompt Guard 2 22M or ShieldGemma 9B open source?
Llama Prompt Guard 2 22M is listed under Llama 3.1 Community. ShieldGemma 9B is listed under 1. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for structured outputs, Llama Prompt Guard 2 22M or ShieldGemma 9B?
Llama Prompt Guard 2 22M has the clearer documented structured outputs signal in this comparison. If structured outputs is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Llama Prompt Guard 2 22M and ShieldGemma 9B?
Llama Prompt Guard 2 22M is available on GroqCloud. ShieldGemma 9B is available on NVIDIA NIM. Provider coverage can affect latency, region availability, compliance posture, and fallback options. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
When should I pick Llama Prompt Guard 2 22M over ShieldGemma 9B?
ShieldGemma 9B fits 16x more tokens; pick it for long-context work and Llama Prompt Guard 2 22M for tighter calls. If your workload also depends on provider fit, start with Llama Prompt Guard 2 22M; if it depends on long-context analysis, run the same evaluation with ShieldGemma 9B.
Continue comparing
Last reviewed: 2026-05-01. Data sourced from public model cards and provider documentation.