Google

Google Gemma 3 4B

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,...

Context window
131Ktokens
Max output
16Ktokens
Input
$0.05/ 1M
Output
$0.10/ 1M

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://neurongate.net/v1",
    api_key="sk-ng-your-api-key",
)

completion = client.chat.completions.create(
    model="google/gemma-3-4b-it",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Cost

Example requestTokensCost
Short prompt1K in$0.00005
Typical chat turn1K in · 500 out$0.0001
Document analysis10K in · 2K out$0.0007
Long context100K in · 10K out$0.006
Estimated cost per request$0.0001

Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.

Frequently asked questions

What is Google Gemma 3 4B?

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,...

How much does Google Gemma 3 4B cost?

Google Gemma 3 4B is priced at $0.05 per 1 million input tokens and $0.1 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).

Does Google Gemma 3 4B support streaming?

Yes, Google Gemma 3 4B supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.

What is the context window of Google Gemma 3 4B?

Google Gemma 3 4B has a context window of 131K tokens (~98K words). Maximum output is 16K tokens.

Does Google Gemma 3 4B support function calling (tools)?

Google Gemma 3 4B does not currently support function calling / tool use.

How do I use Google Gemma 3 4B with NeuronGate?

Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id google/gemma-3-4b-it in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.