Gemma 4 26B A4B — Google | Modeldex

Gemma 4 26B A4B

Active

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...

VisionLong contextBudget

API release

Apr 3, 2026(this month)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

History

Gemma 4 26B A4B became available via the Google API on 2026-04-03.

Training & availability

Google has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 262K tokens.
Input modalities: image, text, video.

Recommended for: vision, long-context, cheap.

Pricing

Input: $0.0800 per 1M tokens
Output: $0.3500 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the google API. Copy, paste, replace the key.

from google import genai

client = genai.Client(api_key="...")
resp = client.models.generate_content(
    model="gemma-4.26b-a4b-it",
    contents="Explain quantum computing in one sentence.",
)
print(resp.text)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.08/1M

Output tokens / month2.0M

@ $0.35/1M

Input cost

$0.4

5.0M × $0.08/1M

Output cost

$0.7

2.0M × $0.35/1M

Total / month

$1.1

$13.2 / year

Popularity

Signals from open-source communities — not a quality measure, but useful for gauging adoption among developers.

🤗

HuggingFace downloads

2.8M/ month

HuggingFace likes

730

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Not enough data

This model has no benchmark scores recorded yet.

Community ratings

No ratings yet. Be the first to rate Gemma 4 26B A4B .