Home/Models/Gemma 4 31B (batch)
Google DeepMind logo

Gemma 4 31B (batch)

by Google DeepMind · Released Apr 2026

Multimodal
Compare
Context
262K tokens (~131 books)
Input $/1M
$0.39
Output $/1M
$0.97
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data updated today
About

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

No benchmark data available yet.

Links
Documentation
BenchGecko API
gemma-4-31b-it-batch
Specifications
  • Typemultimodal
  • Context262K tokens (~131 books)
  • ReleasedApr 2026
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.002
Available On
Google DeepMind logoGoogle DeepMind$0.39
Share & Export
Tweet
Gemma 4 31B (batch) is a proprietary multimodal AI model by Google DeepMind, released in April 2026. Context window: 262K tokens.