google

Google: Gemma 4 26B A4B

Gemma 4 26B A4B from Google is a versatile AI model capable of handling text, images, and videos, with a substantial context length of 262,144 tokens. It supports both reasoning and the use of tools, making it suitable for complex tasks that require integration of different data types. This model stands out as a strong contender for those who need to process multimedia inputs efficiently; however, its price point of $0.07 per million input tokens and $0.34 per million output tokens makes it more expensive than some other options in the market. With a blended benchmark score of 52.0 across four independent benchmarks, it performs adequately but may not be the top choice for those prioritizing high scores on specific tasks like coding or agentic behavior.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.07
per 1M tokens
Output Price
$0.34
per 1M tokens
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 52.0 across 4 benchmarks, last refreshed 2026-07-21. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 42.4
AI Index Coding software engineering tasks 64.9
AI Index Agentic multi-step tool-using tasks 18.1
EQ-Bench emotional understanding in dialogue 70.0
Model ID
google/gemma-4-26b-a4b-it
Vendor
google
Released
April 2026
Tokenizer
Gemma
Input Modalities
image, text, video
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.07/M input and $0.34/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.05
A month of a busy support chatbot 5M in / 2M out $1.03

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-19 $0.07 $0.34 262,144
2026-07-17 $0.10 $0.30 262,144

Strong choice for

Category rankings

Where Google: Gemma 4 26B A4B places across the 18 categories it ranks in. How we rank →

#CategoryScore
#4 Real-Time ChatLatency · of 25 ranked 118
#6 Self-Hosted / LocalCost · of 25 ranked 117
#7 Social Media PostsWriting · of 25 ranked 119
#7 Voice Assistant BackendVoice · of 25 ranked 123
#7 Cheap Bulk InferenceCost · of 25 ranked 137
#9 Video SummarizationVideo · of 25 ranked 150
#10 Video Auto-TaggingVideo · of 25 ranked 123
#17 Bulk Data LabelingData · of 25 ranked 133
#17 Short-Form SummarizationWriting · of 25 ranked 129
#17 Email DraftingWriting · of 25 ranked 125
#17 Language LearningEducation · of 25 ranked 125
#17 Chat CompanionPersonal · of 25 ranked 129
#19 Code CompletionCode · of 25 ranked 132
#20 Image CaptioningVision · of 25 ranked 120
#20 Trivia & General KnowledgePersonal · of 25 ranked 119
#21 Dataset AnnotationResearch · of 25 ranked 140
#22 Customer SupportBusiness · of 25 ranked 131
#23 JSON ExtractionData · of 25 ranked 142

Similar models

Quick answers

How much does Google: Gemma 4 26B A4B cost?
$0.07 per million input tokens and $0.34 per million output tokens.
What is Google: Gemma 4 26B A4B 's context window?
262,144 tokens, roughly 393 pages of text in a single request.
Does Google: Gemma 4 26B A4B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Google: Gemma 4 26B A4B process images?
Yes, it accepts image input.