Meta · language model
Llama Guard 4 12B: pricing, context and benchmarks
Llama Guard 4 12B is a language model from Meta released on April 30, 2025. It costs $0.18 per million input tokens and $0.18 per million output tokens, with a 163.8K-token context window. No independent score has been published for it so far.
What you need to know about Llama Guard 4 12B
Llama Guard 4 12B was released by Meta (United States) on April 30, 2025. It accepts images and text as input and produces text. Its context window reaches 163,840 tokens, larger than 32 % of the models in the registry, and it can write up to 16,384 tokens in one go.
It has been available for about 18 months, long enough for its prices and scores to have settled.
Llama Guard 4 12B pricing
On OpenRouter, Llama Guard 4 12B costs $0.18 per million input tokens and $0.18 per million output tokens. Counting three tokens read for every token written, its average price is $0.18 per million, more expensive than 20 % of paid models (4.2 times cheaper than the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0005. At 1,000 tasks a day, budget $14 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Llama Guard 4 12B. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It does not support tool calling: it is not suited to driving an AI agent that has to act.
- Its knowledge stops at August 2024.
Its weights are open and downloadable from Hugging Face: you can run it on your own machines without sending your data to a third party.
Other Meta models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Llama 4 Maverick | Apr 5, 2025 | $0.3 | 132.2 |
| Llama 4 Scout | Apr 5, 2025 | $0.15 | 129.6 |
| Llama 3.3 70B Instruct | Dec 6, 2024 | $0.16 | — |
| Llama 3.2 1B Instruct | Sep 25, 2024 | $0.07 | — |
| Llama 3.2 3B Instruct | Sep 25, 2024 | $0.12 | — |
| Llama 3.1 70B Instruct | Jul 23, 2024 | $0.4 | — |
| Llama 3.1 8B Instruct | Jul 23, 2024 | $0.06 | — |
Verdict
Llama Guard 4 12B scores 55/100 on our grid, which only uses published figures.
Strengths
- Low price: cheaper than 80 % of paid models.
- Open weights: self-hostable, your data stays with you.
Limitations
- No tool calling: unusable as an agent's brain.
- No independent score published: performance cannot be verified.
Avoid if…
- you are building an agent that must call tools.
Alternatives
- Nemotron 3.5 Content Safety$0.2
- Gemma 3 27B$0.15
- Hunyuan A13B Instruct$0.25
- GLM 4.7 Flash$0.15
- gpt-oss-120b$0.26
- Solar Pro 3$0.26
Comparisons and tools
Learn more
Frequently asked questions
How much does Llama Guard 4 12B cost?
$0.18 per million input tokens and $0.18 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0005.
How big is Llama Guard 4 12B's context window?
163,840 tokens, roughly 123,000 words, with a maximum of 16,384 output tokens.
Can Llama Guard 4 12B run locally?
Yes, its weights are published.
Is Llama Guard 4 12B suitable for an AI agent?
No: without tool calling it cannot act, only answer.
What are the alternatives to Llama Guard 4 12B?
The closest models on price and performance are Nemotron 3.5 Content Safety, Gemma 3 27B, and Hunyuan A13B Instruct.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score