Question 1

What is Gemma 4 E4B IT?

Accepted Answer

Gemma 4 E4B IT is a model from Google Gemini AI, released on Apr 2, 2026. Featuring both Dense and Mixture-of-Experts (MoE) architectures, Gemma 4 is well-suited for tasks like text generation, coding, and reasoning. The models are available in four distinct sizes: **E2B**, **E4B**, **26B A4B**, and **31B**. Their diverse sizes make them deployable in environments ranging from high-end phones to laptops and servers, democratizing access to state-of-the-art AI.

Question 2

How much does Gemma 4 E4B IT cost?

Accepted Answer

On the Respan gateway, input starts at $0.10 per 1M tokens on Featherless, and output starts at $0.20 per 1M tokens on Featherless, after gateway discounts.

Question 3

Which providers serve Gemma 4 E4B IT on Respan?

Accepted Answer

Gemma 4 E4B IT is served by Featherless.

Question 4

What is Gemma 4 E4B IT's context window?

Accepted Answer

Gemma 4 E4B IT accepts up to 33K tokens of context.

Question 5

How do I use Gemma 4 E4B IT with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "gemma-4-e4b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Gemma 4 E4B IT?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Featherless at 11 tokens per second, and the lowest response latency was 1.2 seconds on Featherless. Speed varies with request size and provider.

Question 7

How does Gemma 4 E4B IT score on benchmarks?

Accepted Answer

Gemma 4 E4B IT has 4 published benchmark scores, including LiveCodeBench v6 52%, GPQA Diamond 58.6%, and AIME 2026 (no tools) 42.5%. Each score links to where it was published; the data is collected by llmmetric.com.

Gemma 4 E4B IT

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Certified where it counts.

Benchmarks

Coding1

Reasoning1

Math1

Knowledge1

Apps

Gemma 4 E4B IT FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.