Llama Guard 4 12B
Sold by 3 sellers, timed at 51.8 tok/s, and not scored by Artificial Analysis.
retrieved sha256 · 0bb53a77713f
The same weights, served by one provider at its own list price, read from deepinfra.com. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.
What sellers charge
3 sellers · 1.88x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.144 at DeepInfra to $0.27 at DeepInfra. 1 seller undercuts the $0.18 listed; 1 is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
3,494 requests · 3 endpoints · 30-minute windowOpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.
Every endpoint
3 priced · 2 timed · cheapest first- DeepInfradeepinfra/bf16/flex$0.144$0.144not listedbf16147knot matchednonenonenot matchedno reading
- DeepInfradeepinfra/bf16 · listed$0.18$0.18not listedbf1616knot matchednonenonenot matched99.79%
- DeepInfradeepinfra/bf16/priority$0.27$0.27not listedbf16147knot matchednonenonenot matched99.58%
- DeepInfranot matchednot matchednot matchednot matchedno offer51 tok/s45.2282ms807 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offernot timednone884ms1 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer52 tok/s38.2298ms2,687 reqno offer
Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 1 of the 2 timed routes are slower than it, and the middle route runs at 51.5 tok/s. 1 route answered nothing in the window and is not drawn. The widest median-to-p90 gap is DeepInfra's, 1.36x.
DeepInfra publishes 3 offers and had 3 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.
Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 2 of the 3 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: DeepInfra (deepinfra/bf16) at 96.54% on 20 Nov 2026 and DeepInfra (deepinfra/bf16/priority) at 97.63% on 23 Oct 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.
Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .
What each seller accepts
11 parameters · 3 sellers- frequency_penaltyevery seller
- logit_biasevery seller
- max_tokensevery seller
- min_pevery seller
- presence_penaltyevery seller
- repetition_penaltyevery seller
- seedevery seller
- stopevery seller
- temperatureevery seller
- top_kevery seller
- top_pevery seller
All 11 are accepted by every one of the 3 sellers that publish a list. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.
Price position
342 priced modelsBlended $0.18 per million tokens, 3 in to 1 out: cheaper than 275 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.
Measured quality
145 models with an index · 132 on a design arena boardNot ranked in any Design Arena category.
Epoch AI has not placed Llama Guard 4 12B on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.
Benchmark results
none of 6 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for Llama Guard 4 12B under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.
Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.
