Hoodgen
Sign in
GoogleMultimodalFreeReleased 3 April 2026

Gemma 4 26B A4B (free) pricing, context and benchmark

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Chat with Gemma 4 26B A4B (free)
262K
Input context
33K
Output context
Free
Official input
Free
Official output
n/a
AA index
01 · Model Overview

Everything that matters, in one table

Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.

ModelGemma 4 26B A4B (free)
Model IDgoogle/gemma-4-26b-a4b-it:free
ProviderGoogle
Release date3 April 2026
StatusGenerally available
Input context262,144 tokens
Output context32,768 tokens
Official input pricingFree per 1M tokens
Official output pricingFree per 1M tokens
Cache read pricingNot published
Market input pricingFree per 1M (cheapest route)
Market output pricingFree per 1M (cheapest route)
Input modalitiesimage · text · video
Output modalitiestext
Reasoning controlNot exposed
Tool supportText generation only
TokenizerGemma
Provider routes1 endpoint
Artificial Analysis indexNot published
SpeedNot published
Knowledge cutoffNot publicly stated

Input and output support

ModalityInputOutputBilled at
Text✓ yes✓ yesFree in
Image✓ yesnoFree in
Audionononot supported
Video✓ yesnoFree in
File (PDF)nononot supported
02 · Overview

What is Gemma 4 26B A4B (free)?

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 26B A4B (free) carries a 262K token window, uses the Gemma tokenizer and is served by Google. On Hoodgen it sits in the Multimodal tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.

03 · Release

Release and what changed from the previous version

Released3 April 2026
PropertyGemma 4 31BGemma 4 26B A4B (free)Change
Released20262026Same release window
Context262K262KUnchanged
Max output262K33KChanged
Input price$0.1FreeCheaper
Output price$0.34FreeCheaper
Input modalitiesimage, text, videoimage, text, videoUnchanged
AA index4n/aNewer benchmark run
04 · Capabilities

Features and capabilities

◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
♪
Audio and video
Calls, meetings and screen recordings can be summarised in one pass.
07 · Use cases

What can you do with Gemma 4 26B A4B (free)?

Document understanding
Screenshots, charts, scanned pages and PDFs read in the prompt.
Mixed media briefs
One thread holding text, images and files together.
Extraction
Schema constrained JSON out of messy inputs.
Research synthesis
Several sources condensed with the figures preserved.
09 · Pricing

Gemma 4 26B A4B (free) pricing

Official pricing

List price
Free / 1M in
Free / 1M out
  • 262K context
  • image, text, video input
Cheapest route
Free / 1M in
Free / 1M out
  • 1 route on OpenRouter
  • What Hoodgen routes to first
  • Same model, lower bill

Market pricing, every route

ProviderTierInputOutputCache readUptime 24h
Google AI StudiostandardFreeFreen/a100.0%

API pricing and cost calculator

RatePer callTotalCredits
Cheapest route$0.0000$0.001
List price$0.0000$0.001
10 · Developers

API and developer information

Model IDgoogle/gemma-4-26b-a4b-it:free
Endpointhttps://openrouter.ai/api/v1/chat/completions
Parametersprompt and max_tokens
StreamingYes, server sent events
Modality stringtext+image+video->text
Max prompt tokens262,144
Max completion tokens32,768
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it:free",
    "messages": [{ "role": "user", "content": "Summarise this document." }],
    "max_tokens": 1024
  }'
11 · Limitations

Model limitations

Text only outputIt cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals.
Output cap32,768 tokens per request. Long deliverables have to be chunked.
Benchmarks not publishedArtificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here.
Knowledge cutoffThe provider does not state a fixed cutoff for every release. Verify very recent events against search.
Rate limitsFree routes are rate limited by the provider, so heavy batch jobs should use a paid route.
12 · Comparison

Gemma 4 26B A4B (free) vs other Google models

ModelContextInput /1MOutput /1MAA indexReleased
Gemma 4 26B A4B (free)262KFreeFreen/a2026
Gemini 3.1 Pro Preview1.05M$2$12n/a2026
Gemini 4 Argon1.05M$2$1050Oct 2026
Gemini 4 Carbon1.05M$2$10n/a2026
Gemini 3.1 Pro Preview Custom Tools1.05M$2$12n/a2026
Nano Banana Pro (Gemini 3 Pro Image)131K$2$12n/a2026
13 · Privacy

Privacy and data policy

  • On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
  • Requests route through OpenRouter to Google and are covered by that provider's API terms.
  • Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ

Gemma 4 26B A4B (free) questions, answered

Gemma 4 26B A4B (free) is a multimodal model from Google, released 3 April 2026. Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
✦

Start chatting with Gemma 4 26B A4B (free)

Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.

Open Chat, it is freeCompare all models