Google

Gemma 4 26B A4B (free)

by Googletext+image+video->text1 endpoint

Overview

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...

Capabilities

Text generation
Image understanding
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Deterministic seed

Modalities

Input
ImageTextVideo
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
32.8K tokens
Tokenizer
Gemma
Uptime (24h)
9980.9%

Supported Parameters

include_reasoningmax_tokensreasoningresponse_formatseedtemperaturetool_choicetoolstop_p

Pricing

Per 1M tokens
Free
Added
April 3, 2026
Last synced 9/19/2026