Google: Gemma 4 26B A4B API Pricing
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Input / 1M tokens
$0.06
Output / 1M tokens
$0.33
Cost per request (1K in / 500 out)
$0.0002
~$0.23 per 1M tokens mixed
Specifications
Context Window 262K tokens
Max Output Tokens 0
Vision Support Yes
Function Calling No
Streaming Yes
Modality multimodal
Release Date 2026-04-03
Price history will appear here after the first price change is detected.
More from Google
Multimodal
Input / 1M tokens
$0.30
Output / 1M tokens
$2.50
Context: 1.0M Vision Streaming
Multimodal
Input / 1M tokens
$0.10
Output / 1M tokens
$0.40
Context: 1.0M Vision Streaming
Input / 1M tokens
$0.10
Output / 1M tokens
$0.40
Context: 1.0M Vision Streaming
Multimodal
Input / 1M tokens
$1.25
Output / 1M tokens
$10.00
Context: 1.0M Vision Streaming
Multimodal
Input / 1M tokens
$1.25
Output / 1M tokens
$10.00
Context: 1.0M Vision Streaming
Similar Models from Other Providers
Multimodal
Input / 1M tokens
Variable
Output / 1M tokens
Variable
Context: 2.0M Vision Streaming
Multimodal
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 262K Vision Streaming
Multimodal
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 256K Vision Streaming
Multimodal
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 128K Vision Streaming
Multimodal
Input / 1M tokens
Free
Output / 1M tokens
Free
Context: 128K Vision Streaming