Gemma 4 E4B IT
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.
- Input / output price
- $0.02 / $0.10 per 1M
- Context
- 131K tokens
- Released
- Apr 2, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
2 providers, cheapest first, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/gemma-4-e4b | $0.02/M | $0.10/M |
Featherless featherless/gemma-4-e4b-it | $0.10/M | $0.20/M |
Pricing
Averaged across 2 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.06 per 1M
- Average output
- $0.15 per 1M
- Average cache read
- $0.30 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better54tokens/sacross providers
Time to first token
Lower is better1.9sacross providers
Response latency
Lower is better11sacross providers
Benchmarks
4 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBench v6Google | 52% | Apr 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondGoogle | 58.6% | Apr 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026 (no tools)Google | 42.5% | Apr 2, 2026 |
Apps
Use Gemma 4 E4B IT in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemma 4 E4B IT FAQ
Short answers, built from the data on this page.
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.
On the Respan gateway, Gemma 4 E4B IT costs from $0.02 per 1M input tokens and $0.10 per 1M output tokens on Concentrate, after gateway discounts. Averaged across its 2 providers, it costs $0.06 per 1M input tokens and $0.15 per 1M output tokens.
Gemma 4 E4B IT is available through 2 providers: Concentrate and Featherless.
Gemma 4 E4B IT accepts up to 131K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 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.
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 Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.