Gemma 3 4B API: toman pricing and code
google/gemma-3-4b-it
visionjsonYou are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups
Gemma 3 4B 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": "google/gemma-3-4b-it",
"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="google/gemma-3-4b-it",
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: "google/gemma-3-4b-it",
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 Gemma 3 4B good for?
Gemma 3 4B is one of Google's models. Put "google/gemma-3-4b-it" in the model field and the rest of your code stays as it is. Gemma 3 4B keeps 131,072 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 8 and dearer than 398 of the other paid models in the catalogue.
Capabilities available on this id: 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.
For a back-of-envelope figure: about 57 toman per 1,000-word exchange (14,506 in, 29,013 out, per 1M tokens). 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 Llama Guard 4 12B: Gemma 3 4B works out roughly 2.4× cheaper, and its context window is smaller. 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 1,754 thousand-word requests on Gemma 3 4B, and every 1,000 toman is about 17,544 words of round trip. A job with one million input tokens and one million output tokens comes to 43,519 toman in total. Filling this model's 131,072-token window costs 1,901 toman on the input side alone, which is the real reason to keep conversation history short.
Its nearest relative in the catalogue is "google/lyria-3-clip-preview", and choosing between those two is where most people hesitate. The context windows differ too: 131,072 against 1,048,576 tokens. Maximum answer length differs as well: 16,384 against 65,536 tokens. On parameters, this one takes frequency_penalty, logit_bias, min_p, presence_penalty.
Google has 45 models in our catalogue; the cheapest is Gemma 3 4B at 57 toman per thousand words and the dearest Google Gemini Pro Latest at 5,280. 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 Aion-2.0 at 131,072 tokens.
What to use it for: high-volume work such as classification, tagging and bulk summarising, pulling text and fields out of images, extracting data against a fixed schema.
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
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 | 33 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 75 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 2,321 toman |
Frequently asked
- How do I call Gemma 3 4B 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 "google/gemma-3-4b-it". Nothing else in your code changes.
- What does Gemma 3 4B cost in toman?
- 14,506 toman per 1M input tokens and 29,013 toman per 1M output tokens; a 1,000-word request is around 57 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Gemma 3 4B take?
- Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 16,384 tokens.
- Does Gemma 3 4B 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.