google

Google: Gemma 4 26B A4B

The Google model, Gemma 4 26B A4B, is a multi-modal AI system that can process image, text, and video inputs. It has a context length of 262,144 tokens, allowing for complex conversations and tasks. This model also supports various tools and reasoning capabilities, but it does not provide structured output. For users looking for a high-end AI solution with robust features, the Gemma 4 26B A4B may be worth shortlisting. With its competitive benchmark score of 51.6 across four independent benchmarks, it shows promise in real-world applications. However, its price point is $0.07 per million input tokens and $0.34 per million output tokens, which may be a significant investment for some users. Those with large-scale AI projects or high computational needs may find this model's capabilities and pricing to be a viable option.

Open weights 25.8B parameters, about 14.4 GiB at Q4_K_M: fits comfortably on 4 of 17 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
100/100
price + capability + benchmarks
Input Price
$0.07
per 1M tokens · checked 2026-09-04
Output Price
$0.34
per 1M tokens · checked 2026-09-04
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 51.6 across 4 benchmarks, last refreshed 2026-09-04. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 43.0
AI Index Coding software engineering tasks 64.9
AI Index Agentic multi-step tool-using tasks 18.2
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
2026-08-17 $0.07 $0.34 262,144
2026-08-10 $0.12 $0.40 262,144
2026-07-30 $0.07 $0.34 262,144
2026-07-28 $0.14 $0.42 262,144
2026-07-23 $0.12 $0.35 262,144
2026-07-19 $0.07 $0.34 262,144
2026-07-17 $0.10 $0.30 262,144

Category rankings

Where Google: Gemma 4 26B A4B places across the 5 categories it ranks in. How we rank →

#CategoryScore
#11 Real-Time ChatLatency · of 25 ranked 118
#13 Self-Hosted / LocalCost · of 25 ranked 117
#17 Cheap Bulk InferenceCost · of 25 ranked 137
#21 Social Media PostsWriting · of 25 ranked 119
#21 Voice Assistant BackendVoice · of 25 ranked 123

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.