Gemma 4 26B A4B IT: pricing, context and performance

Overview

Released on April 2, 2026, Gemma 4 26B A4B IT is one of the 14 Google DeepMind models tracked on this site. Its weights are published: you can download it and run it on your own servers, or use one of the 28 API providers that list it on models.dev. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. That makes it 6 months old as of October 22, 2026.

We file it under open-weight models (68 models in this category on the site).

How much does Gemma 4 26B A4B IT cost?

Gemma 4 26B A4B IT costs $0.10 per million input tokens and $0.34 per million output tokens (median of 28 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.003; a thousand of those tasks, $2.68.

That is 2.9 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

Benchmark results

Epoch AI publishes 2 results for Gemma 4 26B A4B IT on our basket's benchmarks: too few to compute a reliable capability index.

• GPQA Diamond (PhD-level science questions): 73.2% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 82.2% — the best tracked model, GPT-5.5 Pro, reaches 100%

Technical specifications

Its context window reaches 262,144 tokens, roughly 393 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 32,768 tokens.

It accepts as input: text and image.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (google/gemma-4-26B-A4B-it). See also our list of open-source models.

When to choose it

Given its category, Gemma 4 26B A4B IT is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

What could replace it?

In the same category, the models closest to Gemma 4 26B A4B IT are:

• Gemma 4 31B IT (Google DeepMind, $0.40 per million output tokens)
• Jamba Mini (AI21 Labs, $0.40 per million output tokens)
• DeepSeek V4 Flash 0731 (DeepSeek, index 68.2)
• MiMo-V2.6-Flash (Xiaomi (MiMo), $0.28 per million output tokens)