Gemma 4 26B MoE
Google
🧠 Language Model
Google's open-weight mixture-of-experts model, 26B total, 4B active parameters for fast inference
Specifications
Input modalitiestext
Output modalitiestext
Capabilitiestools, reasoning
Relative speed●●●●● Blazing
Context window262,144 tokens
Max output32,768 tokens
Tool callingYes
Input price$0.105 / 1M
Output price$0.5775 / 1M
Pricing
$0.105 / 1M input tokens · $0.5775 / 1M output tokens
Platform credit pricing — live rates on the Models page.