Gemma 3 27B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

ChatGoogle262k tokens$0.0872 / $0.4905 · 1M

google/gemma-3-27b-it

Context
262k tokens
Completion cap
131,072
Tools
Yes
JSON
Yes
Released
2025-03-12

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3-27b-it",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Gemma 3 27B?
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it) Gemma 3 27B runs on the Geek Hub API (OpenAI-compatible). Model id: google/gemma-3-27b-it.
Is Gemma 3 27B free?
No. Input is $0.0872 per 1M tokens and output is $0.4905 per 1M tokens on Geek Hub (markup included).
What is the context length of Gemma 3 27B?
Gemma 3 27B has a 262k tokens context window. It supports up to 131,072 completion tokens.
Does Gemma 3 27B support tool calling and structured outputs?
Gemma 3 27B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Gemma 3 27B released?
Gemma 3 27B was released on 2025-03-12.

More models from Google