Which is cheaper, Llama 3.2 1B Instruct or Llama Guard 4 12B?

Llama 3.2 1B Instruct is the cheaper of the two: one 1,000-word request costs about 86 toman, about 1.6× cheaper than Llama Guard 4 12B.

Which one has the larger context window?

Llama Guard 4 12B, with 163,840 tokens.

Llama 3.2 1B Instruct vs Llama Guard 4 12B

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else. On cost, Llama 3.2 1B Instruct comes out about 1.6× cheaper.

Feature	Llama 3.2 1B Instruct	Llama Guard 4 12B
Provider	Meta	Meta
Model id	meta-llama/llama-3.2-1b-instruct	meta-llama/llama-guard-4-12b
Context	60,000 tokens	163,840 tokens
Max output	54,000 tokens	16,384 tokens
Input / 1M tokens	7,833 toman	52,223 toman
Output / 1M tokens	58,315 toman	52,223 toman
≈ one 1,000-word request	86 toman	136 toman
Input caching	No	No
Image input	No	Yes
File input	No	No
Tool calling	No	No
JSON output	No	Yes
Reasoning mode	No	No

Which one for what?

Llama 3.2 1B Instruct

High-volume work where cost per call decides

86 toman per 1,000 words · Model page

Llama Guard 4 12B

Reading screenshots, invoices, and scanned forms
High-volume work where cost per call decides

136 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.2-1b-instruct",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uttapen.ir/v1",
    api_key="sk-up-…",
)

stream = client.chat.completions.create(
    model="meta-llama/llama-3.2-1b-instruct",
    messages=[{"role": "user", "content": "Introduce yourself in one sentence."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.uttapen.ir/v1",
  apiKey: "sk-up-…",
});

const stream = await client.chat.completions.create({
  model: "meta-llama/llama-3.2-1b-instruct",
  messages: [{ role: "user", content: "Introduce yourself in one sentence." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

<?php
// composer require openai-php/client guzzlehttp/guzzle
$client = OpenAI::factory()
    ->withBaseUri('https://api.uttapen.ir/v1')
    ->withApiKey('sk-up-…')
    ->make();

$result = $client->chat()->create([
    'model' => 'meta-llama/llama-3.2-1b-instruct',
    'messages' => [['role' => 'user', 'content' => 'Introduce yourself in one sentence.']],
]);
echo $result->choices[0]->message->content;

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://api.uttapen.ir/v1"),
		option.WithAPIKey("sk-up-…"),
	)
	resp, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
		Model:    "meta-llama/llama-3.2-1b-instruct",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "meta-llama/llama-guard-4-12b"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1