Gemma 4 E4B (Reasoning)+1 tiers
Gemma 4 E4B (Reasoning) is developed by Google, released 2026-04-03.
Reasoning-effort tiers merged. This page shows the
highest-intelligence tier. It merges 2 tiers of the same model:
Gemma 4 E4B (Reasoning), Gemma 4 E4B (Non-reasoning).
Input price
$0.02 / 1M tok
Output price
$0.10 / 1M tok
Blended price
$0.04 / 1M tok
Intelligence
8.9
44th percentile of 554 models with an Intelligence score
Coding
—
Math
—
Speed
45 tok/s
Time to first token
0.40s
Official pricing from Google.
Multi-gateway price comparison (OpenRouter, Together, etc.) is coming soon — not live yet.
See all of Google's models on its provider page, or browse the full model directory.