How much does Gemma 4 26B A4B cost?

Gemma 4 26B A4B costs $0.08 per million input tokens and $0.10 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.000 per message.

Is Gemma 4 26B A4B open source?

Yes, Gemma 4 26B A4B is open source.

How does Gemma 4 26B A4B compare to Qwen3 32B?

Gemma 4 26B A4B has an average score of 47.7 while Qwen3 32B scores 47.7. Qwen3 32B slightly outperforms Gemma 4 26B A4B overall. Gemma 4 26B A4B costs $0.08/1M input vs Qwen3 32B at $0.08/1M input. See full comparison →

Home/Models/Gemma 4 26B A4B

Gemma 4 26B A4B

Name: Gemma 4 26B A4B · benchmarks, pricing and providers
Creator: BenchGecko

by Google DeepMind · Released Apr 2026

Open SourceMultimodal

47.7

avg score

Rank #170

Compare

Better than 48% of all models

Context

262K tokens (~131 books)

Input $/1M

$0.08

Output $/1M

$0.10

Type

multimodal

License

Open Source

Benchmarks

19 tested

Data as of 2026-11-11

About

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...

Tested on 19 benchmarks · BenchGecko score 47.7. Top scores: Chatbot Arena Elo · Overall (1437.5%), Chatbot Arena Elo · Coding (1358.5%), OTIS Mock AIME 2024-2025 (82.2%).

Capabilities

coding

35.2

#161 globally

math

82.2

#26 globally

knowledge

34.0

#247 globally

speed

38.5

#76 globally

general

46.6

#51 globally

Benchmark Scores

Compare All

Tested on 19 benchmarks · Ranked across 6 categories

Score Distribution (all 326 models)

0255075100

▲ You are here

codingCompare coding →

WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

35.2·

mathCompare math →

OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

82.2·

knowledgeCompare knowledge →

GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

67.0·

Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

1.1·

Quick compare:

vs Qwen3 32B

vs Llama 3.3 70B Instruct

vs Qwen3 Max

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Recently Happened

Gemma 4 26B A4B pricing dropped 12%

Nov 7, 2026

Gemma 4 26B A4B pricing dropped 7%

Nov 4, 2026

Gemma 4 26B A4B pricing increased 13%

Oct 29, 2026

Gemma 4 26B A4B pricing dropped 12%

Oct 25, 2026

Gemma 4 26B A4B pricing increased 13%

Oct 20, 2026

Gemma 4 26B A4B pricing dropped 12%

Oct 3, 2026

Similar Models

Qwen3 32B

Alibaba Qwen

47.7$0.08/1M

Llama 3.3 70B Instruct

Frequently Asked Questions

Gemma 4 26B A4B is an open-source multimodal AI model by Google DeepMind, released in April 2026. It has an average benchmark score of 47.7. Context window: 262K tokens.

Benchmarks

Chatbot Arena Elo · Overall Chatbot Arena Elo · Coding OTIS Mock AIME 2024-2025 Artificial Analysis · GPQA Diamond Artificial Analysis · IFBench

Google DeepMind · Provider Google DeepMind · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

Key facts · as of 2026-11-11

Gemma 4 26B A4B by Google DeepMind. BenchGecko score 47.7, rank 169 of 326 scored models (normalized average of public benchmark scores).
List price $0.0800 input · $0.10 output per 1M tokens (as of 2026-11-11).
Sold by 15 providers (as of 2026-11-11): PrimeIntellect (bf16) $0.0110 in / $0.0340 out · Darkbloom $0.0400 in / $0.15 out · DekaLLM (bf16) $0.0600 in / $0.33 out · AkashML (fp4) $0.0700 in / $0.24 out · DeepInfra (fp8) $0.0700 in / $0.34 out · and 10 more. Every provider
Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax B (44% more tokens outside English).

How to cite · data as of 2026-11-11

Gemma 4 26B A4B · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/gemma-4-26b-a4b-it

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP

Gemma 4 26B A4B

Frequently Asked Questions

Related Models

Benchmarks

Related Pages

Key facts · as of 2026-11-11

How to cite · data as of 2026-11-11