Gemma 3 27B Instruct is the 27-billion-parameter instruction-tuned model in Google DeepMind's Gemma 3 family of open-weight multimodal models. It takes text and image input and produces text output, with a 128K-token context window and support for over 140 languages, for tasks such as chat, summarization, question answering and image understanding.
Modalities
In / out price
$0.08 / $0.16per 1M
Context
131K
Max output
16K
Updated
Oct 22, 2026
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
5Streaming
Tool calling
Vision
JSON/schema
Web search
Uptime
FAQ
Common questions about Gemma 3 27B Instruct.