AI model
meta-llama/llama-guard-4-12b
Meta: Llama Guard 4 12B is a 163,840-token model served on Composite at $0.180 per million tokens in and $0.180 per million tokens out.
Try in Playground| Model ID | meta-llama/llama-guard-4-12b |
|---|---|
| Provider | DeepInfra |
| Context window | 163,840 tokens |
| Accepts | image, text |
| Returns | text |
| Input price | $0.180 per million tokens |
| Output price | $0.180 per million tokens |
| Prompt caching | Not offered for this model |
| Moderated | No |
| Cost on a monthly plan | About 1.3 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 2 (base plus 1 routing variant) |
Make a Composite API key and type meta-llama/llama-guard-4-12b as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
The same model behind 1 alternative endpoint. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| cheapThink | meta-llama/llama-guard-4-12b:cheapThink |
DeepInfra | $0.180 per million tokens input · $0.180 per million tokens output |
$0.180 per million tokens input · $0.180 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 1.3 plan credits, at the provider's own price.
DeepInfra
Llama models are a widely-supported open baseline, useful when you want predictable, well-documented behavior.
With a 163,840-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
Supplied by DeepInfra, not written by Composite.
Meta: Muse Ember · Meta: Muse Spark Open · Meta: Muse Wonder