Gemma 4 26B-A4B (Reasoning)

by Google

Gemma 4 26B-A4B (Reasoning) is a reasoning model from Google, released on April 2, 2026. It has a 262K-token context window and can generate up to 262K output tokens. API pricing is $0.07 per 1M input tokens and $0.34 per 1M output tokens. It ranks #82 of 220 models by Intelligence Score with a score of 29.5.

Gemma 4 26B-A4B is Google DeepMind's Mixture-of-Experts multimodal model with 26 billion total parameters and 3.8 billion activated parameters per token, with a 256K context window. Ranks #6 among open models on Arena AI, outcompeting models 20x its size. Achieves an estimated LMArena text score of 1441. Supports image and text inputs.

Key specs

ProviderGoogle
Release date2026-04-02
Licenseopen source
Context window262K tokens
Max output262K tokens
Input price$0.07 / 1M tokens
Output price$0.34 / 1M tokens
Intelligence Score29.5
Output speed182 tokens/s
Time to first token1.87 s

Quick answers

What is the context window of Gemma 4 26B-A4B (Reasoning)?

Gemma 4 26B-A4B (Reasoning) has a context window of 262K tokens, with a maximum output of 262K tokens per response.

How much does Gemma 4 26B-A4B (Reasoning) cost?

Gemma 4 26B-A4B (Reasoning) costs $0.07 per 1M input tokens and $0.34 per 1M output tokens through the API.

Is Gemma 4 26B-A4B (Reasoning) open source?

Yes. Gemma 4 26B-A4B (Reasoning) is an open model released under the open source license.

When was Gemma 4 26B-A4B (Reasoning) released?

Google released Gemma 4 26B-A4B (Reasoning) on April 2, 2026.

How does Gemma 4 26B-A4B (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

Gemma 4 26B-A4B (Reasoning) scores 29.5 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.07 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models

More models from Google