Gemma 4 E4B (Reasoning)

by Google

Gemma 4 E4B (Reasoning) is a reasoning model from Google, released on April 2, 2026. It has a 131K-token context window and can generate up to 131K output tokens. API pricing is $0.02 per 1M input tokens and $0.1 per 1M output tokens. It ranks #149 of 220 models by Intelligence Score with a score of 13.8.

Gemma 4 E4B is Google DeepMind's compact multimodal model with 4.5 billion effective parameters (8B with embeddings) and a 128K context window. Supports image, text, and audio inputs. Features Per-Layer Embeddings for efficient on-device deployment while maintaining strong multimodal capabilities.

Key specs

ProviderGoogle
Release date2026-04-02
Licenseopen source
Context window131K tokens
Max output131K tokens
Input price$0.02 / 1M tokens
Output price$0.1 / 1M tokens
Intelligence Score13.8

Quick answers

What is the context window of Gemma 4 E4B (Reasoning)?

Gemma 4 E4B (Reasoning) has a context window of 131K tokens, with a maximum output of 131K tokens per response.

How much does Gemma 4 E4B (Reasoning) cost?

Gemma 4 E4B (Reasoning) costs $0.02 per 1M input tokens and $0.1 per 1M output tokens through the API.

Is Gemma 4 E4B (Reasoning) open source?

Yes. Gemma 4 E4B (Reasoning) is an open model released under the open source license.

When was Gemma 4 E4B (Reasoning) released?

Google released Gemma 4 E4B (Reasoning) on April 2, 2026.

How does Gemma 4 E4B (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

Gemma 4 E4B (Reasoning) scores 13.8 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.02 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models

More models from Google