Llama Guard 4 12B API: toman pricing and code
meta-llama/llama-guard-4-12b
visionjsonYou are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups
Llama Guard 4 12B example: reading an image into JSON
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/llama-guard-4-12b",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "Return only the invoice number and the total, as JSON."},
{"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
]
}]
}'import base64, json
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
img = base64.b64encode(open("factor.jpg", "rb").read()).decode()
resp = client.chat.completions.create(
model="meta-llama/llama-guard-4-12b",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
],
}],
response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))import OpenAI from "openai";
import { readFileSync } from "node:fs";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");
const resp = await client.chat.completions.create({
model: "meta-llama/llama-guard-4-12b",
messages: [{
role: "user",
content: [
{ type: "text", text: "Return the invoice number, the date and the total as JSON." },
{ type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
],
}],
response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));What is Llama Guard 4 12B good for?
Llama Guard 4 12B is one of Meta's models. Put "meta-llama/llama-guard-4-12b" in the model field and the rest of your code stays as it is. Llama Guard 4 12B keeps 163,840 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 16,384 tokens. On price it sits in the "very cheap" band — cheaper than 29 and dearer than 377 of the other paid models in the catalogue.
What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; it returns schema-valid JSON through response_format, ready to hand to your code. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.
Input runs at 52,223 toman per 1M tokens and output at 52,223 — output costs 1× input, so trimming the answer saves more than trimming the prompt. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.
The closest alternative with the same capabilities from a different provider is UI-TARS 7B : Llama Guard 4 12B works out roughly 1.2× more expensive, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.
To make the figure concrete: 100,000 toman of credit buys roughly 735 thousand-word requests on Llama Guard 4 12B, and every 1,000 toman is about 7,353 words of round trip. A job with one million input tokens and one million output tokens comes to 104,445 toman in total. Filling this model's 163,840-token window costs 8,556 toman on the input side alone, which is the real reason to keep conversation history short.
Meta has 8 models in our catalogue; the cheapest is Llama 3.1 8B Instruct at 49 toman per thousand words and the dearest Llama 4 Maverick at 338. Among the less common parameters it accepts logit_bias, min_p, repetition_penalty, top_k — all through the standard request body. It does not support include_reasoning, reasoning, tool_choice, tools, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is DeepSeek V3 at 163,840 tokens.
Where it makes sense: high-volume work such as classification, tagging and bulk summarising, pulling text and fields out of images, extracting data against a fixed schema.
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...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 99 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 240 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 7,311 toman |
Frequently asked
- How do I call Llama Guard 4 12B from Iran?
- Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "meta-llama/llama-guard-4-12b". Nothing else in your code changes.
- What does Llama Guard 4 12B cost in toman?
- 52,223 toman per 1M input tokens and 52,223 toman per 1M output tokens; a 1,000-word request is around 136 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Llama Guard 4 12B take?
- Up to 163,840 tokens per request, roughly 123k words. A single answer can reach 16,384 tokens.
- Does Llama Guard 4 12B support streaming and image input?
- Streaming (stream=true) works on every model here. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.