All models

Meta Llama/operational

Meta: Llama 3.2 3B Instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

Input / output per 1M

$0.05/$0.33

Get an API key
reasoningopen weights

131K

Context window

tokens

118K

Max output

tokens per reply

91ms

Time to first token

p50, EU region

$0.33

Output price

per 1M tokens

Fit

Where this model earns its place

reasoning

Multi-step reasoning — planning, quantitative analysis, and problems that need deliberation rather than recall.

Data handling

Requests are processed in the EU. Prompts are not used for training, and logs follow the retention period in your contract — zero-retention is available on request.

Specifications

Model

Model ID
meta-llama/llama-3.2-3b-instruct
Provider
Meta Llama
Context length
131K
Max output
118K
Modality
text
Licence
Open Weight

Commercial

Input
$0.05
Output
$0.33
Cached input
—
Deployment
serverless
Availability
operational
Last updated
2026-10-26

Cost

What a month actually costs

WorkloadInput tokensOutput tokensMonthly cost
Prototype1.0M250K$0.13
Production50.0M12.0M$6.46
At scale500.0M120.0M$64.60

Illustrative volumes at list price, excluding cached-input discounts and any committed-use agreement. Your invoice shows the same rates, itemised per key.

Cheaper by caching

Repeated prompts — system instructions, retrieved context, few-shot examples — are billed at the cached-input rate where the model supports it. On long system prompts this is typically the largest single line-item saving.

API

Same SDK, different base URL

cURL

curl https://api.itciphtech.com/v1/chat/completions \
  -H "Authorization: Bearer $CIPHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-3.2-3b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.itciphtech.com/v1",
  apiKey: process.env.CIPHER_API_KEY,
});

const res = await client.chat.completions.create({
  model: "meta-llama/llama-3.2-3b-instruct",
  messages: [{ role: "user", content: "Hello!" }],
});

Need this model on dedicated hardware?

Run it single-tenant, inside your own network boundary, with the operations handled by us.

Private hosting