The AI arena is free today

Open Superagent
GoogleReleased on Apr 2, 2026

Gemma 4 E4B: Benchmarks, Pricing & Context Window

Gemma 4 E4B is a language model from Google, released in April 2026, with multimodal input, a 131K-token context window, and pricing from $0.020/M input and $0.100/M output.

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

Input
Text
Output
Text

Gemma 4 E4B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

High-confidence performance for Gemma 4 E4B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.

Performance by conversation depth

How Gemma 4 E4B holds up as conversations get longer.

Quality Tracker

Gemma 4 E4B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Tue Nov 17 2026
Notice missing or incorrect data?

Gemma 4 E4B pricing

Providers

Gemma 4 E4B starts at $0.0200 per million input tokens and $0.100 per million output tokens via DeepInfra.

ProviderInput $/MCached input $/MOutput $/MContext in / outTTFT p95 sOutput p5 c/sModalities in / out
DeepInfra logoDeepInfra
$0.0200—$0.100131.1K/131.1K
—
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Gemma 4 E4B model size

Gemma 4 E4B has 8 billion parameters. See how it compares to other models in the same parameter range.

Parameters
8B
Small (3–10B)
8B
1B7B70B405B

Gemma 4 E4B context window

Input and output token limits for Gemma 4 E4B, plus how it ranks on long-context understanding.

InputOutput
131Ktokens
131Ktokens
≈ 197 pages of text
131K
8K128K1M

Try now

huggle
Gemma 4 E4Bin Huggle

Make it with
Gemma 4 E4B.

Gemma 4 E4B

Gemma 4 E4B latency

Gemma 4 E4B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.

Gemma 4 E4B examples

Recent arena outputs from Gemma 4 E4B, picked from the highest-ranked matchups.

Gemma 4 E4B license

Gemma 4 E4B is released under the Apache 2.0 license, which permits commercial use, has 8.0B parameters, has a knowledge cutoff of January 2025.

License
Apache 2.0
Commercial use allowed
Parameters
8.0B
Knowledge cutoff
January 2025

Apache License 2.0 - allows commercial use

Gemma 4 E4B resources

Official sources for Gemma 4 E4B: provider documentation, official launch post, model weights.

Gemma 4 E4B vs other models

The most-compared alternatives to Gemma 4 E4B are Gemini 1.5 Pro, Qwen3-235B-A22B-Instruct-2507, DeepSeek R1 Distill Qwen 14B. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Gemma 4 E4B

Models ranked just above and below Gemma 4 E4B by LLM Stats score.

 

Gemini 1.5 Pro

Score pending
 

Qwen3-235B-A22B-Instruct-2507

Score pending
 

DeepSeek R1 Distill Qwen 14B

Score pending
 

Mistral Small 3.2 24B Instruct

Score pending
 

Qwen2.5 VL 72B Instruct

Score pending
 

Kimi K2 Instruct

Score pending

FAQ

Common questions about Gemma 4 E4B.

When was Gemma 4 E4B released?

Gemma 4 E4B was released on April 2, 2026 by Google. This is the official Gemma 4 E4B release date tracked on LLM Stats.

How much does Gemma 4 E4B cost?

Gemma 4 E4B pricing starts at $0.02 per million input tokens and $0.10 per million output tokens via DeepInfra, the lowest price among tracked providers.

How big is Gemma 4 E4B?

Gemma 4 E4B has 8 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Gemma 4 E4B?

Gemma 4 E4B was created by Google.

What is the license for Gemma 4 E4B?

Gemma 4 E4B is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

What is the knowledge cutoff date for Gemma 4 E4B?

Gemma 4 E4B has a knowledge cutoff of January 2025, meaning it was trained on data up to that point and may not know about events after it.

Is Gemma 4 E4B multimodal?

Yes, Gemma 4 E4B is multimodal and can accept both text and images as input.

Where can I use Gemma 4 E4B?

Gemma 4 E4B is available through 1 provider including DeepInfra.

Where is the Gemma 4 E4B paper or technical report?

Gemma 4 E4B has a paper or technical report available at https://huggingface.co/blog/gemma4. Use that source for architecture, training, release and evaluation details.

What models should I compare Gemma 4 E4B against?

Common Gemma 4 E4B comparisons include Gemma 4 E4B vs Gemini 1.5 Pro, Gemma 4 E4B vs Qwen3-235B-A22B-Instruct-2507, Gemma 4 E4B vs DeepSeek R1 Distill Qwen 14B. Compare them side by side for benchmark scores, pricing, context window, latency and provider availability.