Gemma 4 31B (batch)

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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

ChatGoogle262k tokens$0.4251 / $1.0574 · 1M

google/gemma-4-31b-it:batch

Context
262k tokens
Completion cap
235,929
Tools
Yes
JSON
Yes
Released
2026-04-02

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-4-31b-it:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Gemma 4 31B (batch)?
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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license. Gemma 4 31B (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: google/gemma-4-31b-it:batch.
Is Gemma 4 31B (batch) free?
No. Input is $0.4251 per 1M tokens and output is $1.0574 per 1M tokens on Geek Hub (markup included).
What is the context length of Gemma 4 31B (batch)?
Gemma 4 31B (batch) has a 262k tokens context window. It supports up to 235,929 completion tokens.
Does Gemma 4 31B (batch) support tool calling and structured outputs?
Gemma 4 31B (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Gemma 4 31B (batch) released?
Gemma 4 31B (batch) was released on 2026-04-02.

More models from Google