Google: Gemma 3 4B

by Google · Released 2025-03-13

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,...

Try it in Chat Lab Compare Top up

Modalities

TextImagesText

Two kinds of input in one request · replies with text only

Price per 1M tokens

in16,20 DAout32,40 DA

A typical exchange costs about 0,03 DA

Context131K tokensMax output16.4K tokensReleased2025-03-13

On this page

What it can do

Real jobs this model can take on, based on what it can read and how it’s priced.

Turn a screenshot of a design into working code

understands images

Power a chat product at high volume, priced per reply

≈ 0,03 DA per typical reply

Good for

High-volume workloads where cost per reply matters

Not for

Generating images — it replies with text only
Speaking its replies aloud — no audio output
Fine-tuning on your own data — not supported

Also supports

Tool callingStructured JSONStep-by-step reasoningStreamingPrompt cachingFine-tuning

Where your request runs

You call one endpoint. Behind it, OpenDunes keeps every one of these live — if one degrades, the next takes the request without you changing a line.

Provider	In /M	Out /M	Cache /M	Latency	TPS	Uptime
DeepInfra	16,20 DA	32,40 DA	—	—	—	100,0 %

Routed through the Bifrost gateway · prices in Algerian Dinars per 1M tokens · you’re charged the price of the endpoint that served your request.

What it costs

Everyday jobs, priced. Each request charges exactly what it uses — no subscription, no minimum.

Answer a quick question≈ 0,0068 DA

Reply to a customer email≈ 0,02 DA

Read an invoice photo and pull out the total≈ 0,04 DA

Translate a full page of text≈ 0,03 DA

Write a one-page draft≈ 0,03 DA

Top up points

3 000 DA ≈ 115 740 typical replies · the exact charge appears after every request, down to the centime.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Understands images

You send

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photo

It replies

The total is 42 300,00 DA, due September 3, 2026. Worth a double-check: the handwritten day could read as an 8 instead of a 3.

Try in Chat Lab

Structured output

You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt

It replies

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.

EndpointPOST /v1/chat/completions

Base URL

https://opendunes.com/api/v1

Model id

google/gemma-3-4b-it

Shell

curl https://opendunes.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENDUNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3-4b-it",
    "messages": [{"role": "user", "content": "In one sentence: why is the sky blue?"}]
  }'

The same request, in your language

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_bias

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window: 131K tokens
Max output: 16.4K tokens
Longest reply: ≈ 12.0K words
Tokenizer: Gemini
Knowledge cutoff: 2024-08-31
Released: 2025-03-13

Full API reference Open weights on Hugging Face

Questions about Gemma 3 4B

How much does Gemma 3 4B cost in Algerian Dinars?

16,20 DA for the text you send and 32,40 DA for the text it writes back. A typical exchange — a short question and a one-screen answer — costs about 0,03 DA. You pay for what you actually use: no subscription, no minimum.

How big is Gemma 3 4B's context window?

Gemma 3 4B reads up to 131K tokens in one request, and writes back up to roughly 12,000 words at once.

What can Gemma 3 4B handle?

It reads text and images and replies with text. It also supports replying in structured JSON and streaming its answer as it writes.

Can I use Gemma 3 4B without an international bank card?

Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on Gemma 3 4B or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.

Who makes Gemma 3 4B?

Gemma 3 4B is built by Google, released on Mar 13, 2025. Its training data runs to 2024-08-31. OpenDunes serves it unchanged — same model, same weights, billed in dinars.

Other Google models, priced in dinars

See all Google models

Google: Gemini 3.7 Flash

google/gemini-3.7-flashText

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

by GoogleAug 13, 20261M contextReasoningToolsJSON

TextImagesVideoAudioFilesText

in243 DAout1 215 DAper 1M tokens

by GoogleAug 13, 20261M contextReasoningToolsJSON

Google: Gemini 3.7 Flash (batch)

google/gemini-3.7-flash:batchText

by GoogleAug 13, 20261M contextReasoningToolsJSON

TextImagesVideoAudioFilesText

in60,75 DAout303,75 DAper 1M tokens

by GoogleAug 13, 20261M contextReasoningToolsJSON

Google: Gemini 3.6 Flash

google/gemini-3.6-flashText

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

by GoogleJul 21, 20261M contextReasoningToolsJSON

TextImagesVideoAudioFilesText

in243 DAout1 215 DAper 1M tokens

by GoogleJul 21, 20261M contextReasoningToolsJSON

Google: Gemini 3.6 Flash (batch)

google/gemini-3.6-flash:batchText

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

by GoogleJul 21, 20261M contextReasoningToolsJSON

TextImagesVideoAudioFilesText

in121,50 DAout607,50 DAper 1M tokens

by GoogleJul 21, 20261M contextReasoningToolsJSON

Google: Gemini 3.5 Flash Lite

google/gemini-3.5-flash-liteText

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

by GoogleJul 21, 20261M contextReasoningToolsJSON

TextImagesVideoAudioFilesText

in97,20 DAout810 DAper 1M tokens

by GoogleJul 21, 20261M contextReasoningToolsJSON

Google: Gemini 3.5 Flash Lite (batch)

google/gemini-3.5-flash-lite:batchText

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

by GoogleJul 21, 20261M contextReasoningToolsJSON

TextImagesVideoAudioFilesText

in48,60 DAout405 DAper 1M tokens

by GoogleJul 21, 20261M contextReasoningToolsJSON

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

google/gemini-3.1-flash-lite-imageImage

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

by GoogleJun 30, 202666K contextReasoningJSON

TextImagesTextImages

81 DA/M input·486 DA/M output

by GoogleJun 30, 202666K contextReasoningJSON

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

google/gemini-3.1-flash-imageImage

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

by GoogleJun 18, 2026131K contextReasoningJSON

TextImagesTextImages

162 DA/M input·972 DA/M output

by GoogleJun 18, 2026131K contextReasoningJSON

Google: Gemma 3 4B

What it can do

Good for

Not for

Also supports

Where your request runs

What it costs

See it in action

Call it in code

Pythonopenai SDK · pip install openai

JavaScriptopenai npm package · Node 18+

Goopenai-go · go get github.com/openai/openai-go

Parameters you can send

Limits

Questions about Gemma 3 4B

How much does Gemma 3 4B cost in Algerian Dinars?

How big is Gemma 3 4B's context window?

What can Gemma 3 4B handle?

Can I use Gemma 3 4B without an international bank card?

Who makes Gemma 3 4B?

Other Google models, priced in dinars

Google: Gemini 3.7 Flash

Google: Gemini 3.7 Flash (batch)

Google: Gemini 3.6 Flash

Google: Gemini 3.6 Flash (batch)

Google: Gemini 3.5 Flash Lite

Google: Gemini 3.5 Flash Lite (batch)

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

Google: Gemma 3 4B

What it can do

Good for

Not for

Also supports

Where your request runs

What it costs

See it in action

Call it in code

Pythonopenai SDK · pip install openai

JavaScriptopenai npm package · Node 18+

Goopenai-go · go get github.com/openai/openai-go

Parameters you can send

Limits

Questions about Gemma 3 4B

How much does Gemma 3 4B cost in Algerian Dinars?

How big is Gemma 3 4B's context window?

What can Gemma 3 4B handle?

Can I use Gemma 3 4B without an international bank card?

Who makes Gemma 3 4B?

Other Google models, priced in dinars

Google: Gemini 3.7 Flash

Google: Gemini 3.7 Flash (batch)

Google: Gemini 3.6 Flash

Google: Gemini 3.6 Flash (batch)

Google: Gemini 3.5 Flash Lite

Google: Gemini 3.5 Flash Lite (batch)

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Google: Nano Banana 2 (Gemini 3.1 Flash Image)