Llama Prompt Guard 2 22M vs Trinity-Large-Preview
Llama Prompt Guard 2 22M (2025) and Trinity-Large-Preview (2026) are compact production models from AI at Meta and Arcee AI. Llama Prompt Guard 2 22M ships a 512-token context window, while Trinity-Large-Preview ships a 128k-token context window. On pricing, Llama Prompt Guard 2 22M costs $0.03/1M input tokens versus $0.15/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Llama Prompt Guard 2 22M is ~400% cheaper at $0.03/1M; pay for Trinity-Large-Preview only for long-context analysis.
Decision scorecard
Local evidence first| Signal | Llama Prompt Guard 2 22M | Trinity-Large-Preview |
|---|---|---|
| Best for | general production evaluation | tool-calling agents and provider-routed production |
| Decision fit | Classification and JSON / Tool use | RAG, Agents, and Long context |
| Context window | 512 | 128k |
| Cheapest output | $0.03/1M tokens | $0.45/1M tokens |
| Provider routes | 1 tracked | 3 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Llama Prompt Guard 2 22M has the lower cheapest tracked output price at $0.03/1M tokens.
- Local decision data tags Llama Prompt Guard 2 22M for Classification and JSON / Tool use.
- Trinity-Large-Preview has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Trinity-Large-Preview has broader tracked provider coverage for fallback and procurement flexibility.
- Trinity-Large-Preview uniquely exposes Function calling and Tool use in local model data.
- Local decision data tags Trinity-Large-Preview for RAG, Agents, and Long context.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Llama Prompt Guard 2 22M
$31.50
Cheapest tracked route/tier: GroqCloud
Trinity-Large-Preview
$233
Cheapest tracked route/tier: OpenRouter
Estimated monthly gap: $201. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- No overlapping tracked provider route is sourced for Llama Prompt Guard 2 22M and Trinity-Large-Preview; plan for SDK, billing, or endpoint changes.
- Trinity-Large-Preview is $0.42/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Trinity-Large-Preview adds Function calling and Tool use in local capability data.
- No overlapping tracked provider route is sourced for Trinity-Large-Preview and Llama Prompt Guard 2 22M; plan for SDK, billing, or endpoint changes.
- Llama Prompt Guard 2 22M is $0.42/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Function calling and Tool use before moving production traffic.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-04-29 | 2026-01-27 |
| Context window | 512 | 128k |
| Parameters | 22M | 400B |
| Architecture | decoder only | Sparse Mixture of Experts (MoE) |
| License | Llama 3.1 Community | Apache 2.0 |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Llama Prompt Guard 2 22M | Trinity-Large-Preview |
|---|---|---|
| Input price | $0.03/1M tokens | $0.15/1M tokens |
| Output price | $0.03/1M tokens | $0.45/1M tokens |
| Providers |
Capabilities
| Capability | Llama Prompt Guard 2 22M | Trinity-Large-Preview |
|---|---|---|
| Vision | No | No |
| Multimodal | No | No |
| Reasoning | No | No |
| Function calling | No | Yes |
| Tool use | No | Yes |
| Structured outputs | Yes | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on function calling: Trinity-Large-Preview and tool use: Trinity-Large-Preview. Both models share structured outputs, 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.
For cost, Llama Prompt Guard 2 22M lists $0.03/1M input and $0.03/1M output tokens on the cheapest tracked provider, while Trinity-Large-Preview lists $0.15/1M input and $0.45/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Llama Prompt Guard 2 22M lower by about $0.21 per million blended tokens. Availability is 1 providers versus 3, so concentration risk also matters.
Choose Llama Prompt Guard 2 22M when provider fit and lower input-token cost are central to the workload. Choose Trinity-Large-Preview when long-context analysis, larger context windows, and broader provider choice 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.
FAQ
Which has a larger context window, Llama Prompt Guard 2 22M or Trinity-Large-Preview?
Trinity-Large-Preview supports 128k 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.
Which is cheaper, Llama Prompt Guard 2 22M or Trinity-Large-Preview?
Llama Prompt Guard 2 22M is cheaper on tracked token pricing. Llama Prompt Guard 2 22M costs $0.03/1M input and $0.03/1M output tokens. Trinity-Large-Preview costs $0.15/1M input and $0.45/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Llama Prompt Guard 2 22M or Trinity-Large-Preview open source?
Llama Prompt Guard 2 22M is listed under Llama 3.1 Community. Trinity-Large-Preview is listed under Apache 2.0. 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 function calling, Llama Prompt Guard 2 22M or Trinity-Large-Preview?
Trinity-Large-Preview has the clearer documented function calling signal in this comparison. If function calling is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for tool use, Llama Prompt Guard 2 22M or Trinity-Large-Preview?
Trinity-Large-Preview has the clearer documented tool use signal in this comparison. If tool use 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 Trinity-Large-Preview?
Llama Prompt Guard 2 22M is available on GroqCloud. Trinity-Large-Preview is available on OpenRouter, Arcee AI, and Vercel AI Gateway. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-05-22. Data sourced from public model cards and provider documentation.