Gemma 4 26B A4B Instruct is the Mixture-of-Experts model in Google DeepMind's open-weight Gemma 4 family, with 25.2B total and 3.8B active parameters per token. It takes text and image input and produces text output, with a 256K-token context window, configurable thinking and native function calling.
Modalities
In / out price
$0.07 / $0.34per 1M
Cached price
$0.05per 1M
Context
262K
Max output
16K
Providers
2 routesCompare providers by price, privacy, and speed.
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
7Streaming
Tool calling
Reasoning
Vision
JSON/schema
Web search
Prompt caching
Uptime
FAQ
Common questions about Gemma 4 26B A4B Instruct.