per 1M tokens
meta-llama/Llama-Guard-4-12B
deepinfra/meta-llama/Llama-Guard-4-12B
Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It itself acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.36 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.18/1M | $0.18/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.18 | $0.18 | Not published— |
| 2026-10-09 | token | $0.18 | $0.18 | Not published— |
| 2026-10-10 | token | $0.18 | $0.18 | Not published— |
| 2026-10-11 | token | $0.18 | $0.18 | Not published— |
| 2026-10-12 | token | $0.18 | $0.18 | Not published— |
| 2026-10-13 | token | $0.18 | $0.18 | Not published— |
| 2026-10-14 | token | $0.18 | $0.18 | Not published— |
| 2026-10-15 | token | $0.18 | $0.18 | Not published— |
| 2026-10-16 | token | $0.18 | $0.18 | Not published— |
| 2026-10-17 | token | $0.18 | $0.18 | Not published— |
| 2026-10-18 | token | $0.18 | $0.18 | Not published— |
| 2026-10-19 | token | $0.18 | $0.18 | Not published— |
| 2026-10-20 | token | $0.18 | $0.18 | Not published— |
| 2026-10-21 | token | $0.18 | $0.18 | Not published— |
| 2026-10-22 | token | $0.18 | $0.18 | Not published— |
| 2026-10-23 | token | $0.18 | $0.18 | Not published— |
| 2026-10-24 | token | $0.18 | $0.18 | Not published— |
| 2026-10-25 | token | $0.18 | $0.18 | Not published— |
| 2026-10-26 | token | $0.18 | $0.18 | Not published— |
| 2026-10-27 | token | $0.18 | $0.18 | Not published— |
| 2026-10-28 | token | $0.18 | $0.18 | Not published— |
| 2026-10-29 | token | $0.18 | $0.18 | Not published— |
| 2026-10-30 | token | $0.18 | $0.18 | Not published— |
Alternatives
- DeepSeek R1 Distill Qwen 1.5B$0.18/1M · Compare
- Llama 4 Scout Instruct$0.18/1M · Compare
- Llama 4 Scout Instruct (17Bx16E)$0.18/1M · Compare
- Meta Llama 3.1 8B Instruct Turbo$0.18/1M · Compare
- Meta: Llama Guard 4 12B$0.18/1M · Compare
- Qwen3-VL-8B-Instruct$0.18/1M · Compare
Parameters (3)
chatvlmvision
Call this model
OpenRouter id deepinfra/meta-llama/Llama-Guard-4-12B. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepinfra/meta-llama/Llama-Guard-4-12B","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepinfra/meta-llama/Llama-Guard-4-12B",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepinfra/meta-llama/Llama-Guard-4-12B", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())