Enterprise DNAEnterprise DNA
Google logo

Models · Best vision

Gemma 3 4B

by Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Our verdict

Not reviewed yet

We have not reviewed Gemma 3 4B yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Gemma 3 4B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Notes

Gemma 3 4B is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.040 per million tokens
Checked OpenRouter models API
Output price
$0.050 per million tokens
Checked OpenRouter models API
Price on deepinfra
$0.040 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$0.080 per million output tokens
Checked OpenRouter models API
Price on parasail
$0.020 per million cached input tokens
Checked OpenRouter models API
Price on parasail
$0.040 per million input tokens
Checked OpenRouter models API
Price on parasail
$0.050 per million output tokens
Checked OpenRouter models API
Latest version
google/gemma-3-4b-it
Checked OpenRouter models API
Time to first token (ms) on deepinfra
2,498
Checked OpenRouter models API
Gpqa diamond
23.2% (for 12 Mar 2025)
Checked Epoch AI (CC BY 4.0)
Dtbench
50.9% (for 12 Mar 2025)
Checked Epoch AI (CC BY 4.0)
Lmca
2.8% (for 12 Mar 2025)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `google/gemma-3-4b-it`.

  • openrouter · google/gemma-3-4b-it · Docs

OpenRouter id: google/gemma-3-4b-it

Price

What Gemma 3 4B costs, over time

Input price

$0.050 to $0.040

US dollars per million input tokens. 3 Sept 2026 to 21 Nov 2026, 55 days.

Source: OpenRouter models API. Checked .

Output price

$0.100 to $0.050

US dollars per million output tokens. 3 Sept 2026 to 21 Nov 2026, 55 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
deepinfraInput$0.040 per million input tokensSince 15 Nov 20261 changeOpenRouter models API
deepinfraOutput$0.080 per million output tokensSince 15 Nov 20261 changeOpenRouter models API
parasailCached input$0.020 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.040 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$0.050 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Gemma 3 4B is used

Tokens served a day

212.8M to 258.5M

tokens a day on OpenRouter. 19 Sept 2026 to 21 Nov 2026, 64 readings.

Source: OpenRouter model activity (772 of 772 series). Checked .

Scores

How Gemma 3 4B scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index4.8indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index2.7indexAs of 17 Nov 2026Artificial Analysis via OpenRouter
Dtbench (best-across-versions)50.9percentAs of 12 Mar 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)23.2percentAs of 12 Mar 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)2.8percentAs of 12 Mar 2025Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated7.5percentAs of 12 Mar 2025Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 0.1 to 0.05

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.05 to 0.04

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 0.1 to 0.08

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.05 to 0.04

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 0.05 to 0.1

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.04 to 0.05

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 0.1 to 0.05

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.05 to 0.04

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Gemma 3 4B is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
4.6B ▼37.8%
Requests, last 7 days
6.3M
Tool calls, last 7 days
9
Average cost per request
0.5¢
Price per million tokens
$0.04 in · $0.05 out
01.3B2.5B19 Sept: 213M tokens, 189K requests20 Sept: 234M tokens, 111K requests21 Sept: 215M tokens, 95.2K requests22 Sept: 210M tokens, 302K requests23 Sept: 277M tokens, 1.5M requests24 Sept: 225M tokens, 2.9M requests25 Sept: 163M tokens, 2.5M requests26 Sept: 141M tokens, 2.7M requests27 Sept: 227M tokens, 2.6M requests28 Sept: 144M tokens, 212K requests29 Sept: 152M tokens, 178K requests30 Sept: 173M tokens, 150K requests1 Oct: 184M tokens, 200K requests2 Oct: 89.7M tokens, 134K requests3 Oct: 88.2M tokens, 122K requests4 Oct: 73.2M tokens, 108K requests5 Oct: 80.4M tokens, 130K requests6 Oct: 90.5M tokens, 168K requests7 Oct: 111M tokens, 110K requests8 Oct: 112M tokens, 108K requests9 Oct: 108M tokens, 108K requests10 Oct: 69.3M tokens, 89.9K requests11 Oct: 168M tokens, 120K requests12 Oct: 101M tokens, 130K requests13 Oct: 86.6M tokens, 188K requests14 Oct: 118M tokens, 248K requests15 Oct: 231M tokens, 252K requests16 Oct: 193M tokens, 139K requests17 Oct: 106M tokens, 142K requests18 Oct: 222M tokens, 161K requests19 Oct: 134M tokens, 138K requests20 Oct: 173M tokens, 216K requests21 Oct: 157M tokens, 204K requests22 Oct: 267M tokens, 510K requests23 Oct: 235M tokens, 3.1M requests24 Oct: 185M tokens, 3.9M requests25 Oct: 280M tokens, 3.9M requests26 Oct: 285M tokens, 223K requests27 Oct: 486M tokens, 1M requests28 Oct: 661M tokens, 808K requests29 Oct: 766M tokens, 1.2M requests30 Oct: 1.5B tokens, 6.4M requests31 Oct: 1.1B tokens, 5.2M requests1 Nov: 545M tokens, 713K requests2 Nov: 630M tokens, 767K requests3 Nov: 634M tokens, 1.4M requests4 Nov: 675M tokens, 792K requests5 Nov: 542M tokens, 630K requests6 Nov: 445M tokens, 525K requests7 Nov: 761M tokens, 688K requests8 Nov: 1B tokens, 870K requests9 Nov: 671M tokens, 1.1M requests10 Nov: 2.1B tokens, 4.4M requests11 Nov: 1.3B tokens, 1M requests12 Nov: 1B tokens, 1.1M requests13 Nov: 883M tokens, 1.1M requests14 Nov: 404M tokens, 465K requests15 Nov: 731M tokens, 1.4M requests16 Nov: 1.3B tokens, 1.5M requests17 Nov: 1.1B tokens, 1.4M requests18 Nov: 385M tokens, 458K requests19 Nov: 338M tokens, 374K requests20 Nov: 507M tokens, 876K requests21 Nov: 258M tokens, 284K requests19 Sept3 Oct17 Oct31 Oct14 Nov21 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Gemma 3 4B.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-22. Hosting routes and app features can differ.

DeveloperGoogle
Exact model identifiergoogle/gemma-3-4b-it
Inputtext, image
Outputtext
Tool calling
Not established
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Gemma Terms of Use, open weights (access request)
Context length
131K tokens
Knowledge cutoff
31 Aug 2024
Developer release date
Not established
First seen in the catalogue
13 Mar 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

google/gemma-3-4b-it: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-22
openrouter.ai ↗

Source for first seen, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-22
Licence source ↗

Licence declared in the google/gemma-3-4b-it model repository on Hugging Face, which holds the weights files behind an access request. Read the licence terms before use.

Checked 2026-11-21
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 21 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 2.7 (2026-11-17) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.