Google: Gemma 3 4B IT

Open multimodal Gemma instruction model for efficient text generation and image understanding

Model lab: Google
Model family: gemma

Model resources

Hugging Face

Modalitiestext, image → text

Context window131,072

Maximum output131,072

InputUSD 0.04 / 1M tokens

OutputUSD 0.08 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/google/gemma-3-4b-it.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/google/gemma-3-4b-it"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Gemma 3 4B IT API Pricing

Type	Price information
Input	USD 0.04 / 1M tokens
Output	USD 0.08 / 1M tokens

Performance

Performance trends

Throughput93.3 tok/sCurrent

Time to first token1.2 sCurrent

End-to-end latency7.7 sCurrent

Throughput

Current93.3 tok/s

Window average89.6 tok/s

Time to first token

Current1.2 s

Window average1.5 s

End-to-end latency

Current7.7 s

Window average7.5 s

Tail latency (P99)

Current31.8 s

Window average17.5 s

Prompt cache hit rate

Current26.4%

Window average23.3%

Error rate

Current2.1%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Gemma 3 4B IT Compare models

Model	Input price	Output price	Context window	Capabilities
Gemma 3 4B ITThis page	USD 0.04 / 1M tokens	USD 0.08 / 1M tokens	131,072	Text output · Tool calling
Gemma 4 12B IT	USD 0.04 / 1M tokens · Context ≤ 131072 tokens · Maximum output 32768 tokens · Maximum input 131072 tokens	USD 0.2 / 1M tokens · Context ≤ 131072 tokens · Maximum output 32768 tokens · Maximum input 131072 tokens	262,144	Text output · Reasoning · Tool calling
Gemma 4 26B A4B IT	USD 0.0336 / 1M tokens	USD 0.176 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Gemma 4 31B IT	USD 0.08 / 1M tokens	USD 0.2 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Gemma 3 12B IT	USD 0.04 / 1M tokens	USD 0.12 / 1M tokens	131,072	Text output · Tool calling

Model specifications

Input: text, image
Output: text
Context window: 131,072
Maximum output: 131,072
Release date: 2025-03-12
Attachments: Yes
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Gemma 3 4B IT for?

Open multimodal Gemma instruction model for efficient text generation and image understanding

What inputs and outputs does Gemma 3 4B IT support?

Recorded inputs: text, images; outputs: text.

How is Gemma 3 4B IT priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.04 / 1M tokens; Output USD 0.08 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Gemma 3 4B IT?

Current model records list Context window 131,072 tokens; Maximum output 131,072 tokens.

What model parameter does the Quickstart use?

The example uses moduck/google/gemma-3-4b-it. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.