Gemma 4 26B A4B IT
JSON →A 26-billion-parameter instruction-tuned model from Google's Gemma 4 family, using a 4-billion active parameter mixture-of-experts architecture.
Specs
context window 256K tokens
max output 128K tokens
input price $0.15 / 1M tokens
output price $0.6 / 1M tokens
Capabilities
code-generationreasoningstreamingopen-weightsfine-tunablefunction-callingtool-usevision
Dates
releasedApr 2025
Resources
homepageai.google.dev/gemma/docs ↗
API
full doc /v1/models/gemma-4-26b-a4b-it