Google: Gemma 4 26B A4B (free), Google — route, pricing & source

Name: Google: Gemma 4 26B A4B (free) pricing record
Creator: Google

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...

OpenRoutermediumLast checked: Jun 2, 2026

Input

$0.00 / 1M

/ 1M tokens

Output

$0.00 / 1M

/ 1M tokens

Cached input

Not available

Cache write

Not available

Context and limits

Context window

262.1K

Max output

32,768

Input modalities

image, text, video

Output modalities

text

Weight access

Open weights

Availability

Unknown

Capability flags

VisionToolsJSONReasoningLong context

From source metadata + verification fields — confirm provider docs before production.

Benchmarks

Access and license

Official API

Open weights

Self-hostable

License

Open sourceApache 2.0Code/weights ship under an open license (often MIT / Apache‑2.0). MIT is a short permissive license: use/modify/redistribute freely with a copyright notice—always read the upstream project text.

Example costs

Scenario: 1K input + 300 output tokens / request

10,000 requests

$0.00

100,000 requests

$0.00

1,000,000 requests

$0.00

Cheaper alternatives

Lower-cost models for the same scenario

No cheaper alternative for this scenario.

Source

OpenRouter Models API

Confidence

medium

Route

OpenRouter

Last checked

Jun 2, 2026

Source notes

Includes Hugging Face benchmark data only when the dataset is public, ungated, allowlisted, and matched by reviewed aliases.

Open source