Llama Guard 4 12B is a language model from Meta. It does not hold a position on ModelCap's current board yet; it is placed automatically once its model card or a public benchmark compares it with ranked models. It is listed at $0.18 per million input tokens and $0.18 per million output tokens from one provider. It reads up to 164K tokens of context, and its weights are downloadable after an access request.
Figures as of 7 Nov 2026, 13:42 UTC · download the public dataset · methodology
Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.
Not yet published: the base model it derives from, a link to the licence terms, measured provider uptime, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
meta-llama/llama-guard-4-12bOpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata
Gated access. The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution.
Llama Guard 4 12B has no public ModelCap Index position as of 7 November 2026: the snapshot lacks enough matched benchmark evidence, or the identity match is unresolved. Its catalogue facts (price, context, providers) are shown without a rank.
Llama Guard 4 12B is listed at $0.18 per 1M input tokens and $0.18 per 1M output tokens as of 7 November 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $0.45 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.
Llama Guard 4 12B has a published context window of 164K tokens (163,840). The snapshot lists a 16,384 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.
Gated access (llama4). The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution. The repository is meta-llama/Llama-Guard-4-12B on Hugging Face.
One provider serves Llama Guard 4 12B through OpenRouter as of 7 November 2026: DeepInfra. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Llama Guard 4 12B first appeared in the catalogue on 30 Apr 2025, with a published knowledge cutoff of 2024-08-31. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.