This is the asynchronous batch endpoint for Google's Gemini 4 Hydrogen, the high-efficiency workhorse of the Gemini 4 family (1M-token context, multimodal input). It runs at half the standard rate ($0.75/$3.75 per million input/output tokens), which suits bulk coding, extraction, and evaluation jobs that do not need immediate responses.
Cost rate
0.8x
Context
1M
Released
Nov 12, 2026
Input
AudioFileImageTextVideo
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Legal & Government
#6 路 top 2%
Entertainment, Sports, & Media
#7 路 top 2%
Mathematical
#9 路 top 2%
Writing, Literature, & Language
#12 路 top 3%