Google

Google: Gemma 4 31B

google/gemma-4-31b-it-20260402Hugging Face ↗

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...

toolsstructuredreasoningimage in
Data source

Google: Gemma 4 31B usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

Google: Gemma 4 31B holds 0.28% today, down from 0.38% at the start of the visible window.

Data: OpenRouter as of 2026-10-08 · Source: tidelines.ai/models/google-gemma-4-31b-it-20260402

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-10-08 · Source: tidelines.ai/models/google-gemma-4-31b-it-20260402

Adoption curve vs the pantheon

Google: Gemma 4 31B's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-10-08 · Source: tidelines.ai/models/google-gemma-4-31b-it-20260402

Citable stat

As of 2026-10-08, Google: Gemma 4 31B holds 0.3% of OpenRouter token share, down 0.03pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one Google: Gemma 4 31B session, by coding agent and session length.

Tidelines — LLM usage and market share

Token rate sets the price; session length and reasoning set the bill.

Agent1 turn2–9 turns10–49 turns
Hermes Agent$0.0017$0.0075$0.093

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-09-27 · Source: tidelines.ai/models/google-gemma-4-31b-it-20260402

Where to run it

Google: Gemma 4 31B pricing by provider

Tidelines — LLM usage and market share

Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.

Google: Gemma 4 31B is served by 13 tracked endpoints on OpenRouter. The cheapest output price is $0.34 per million tokens from DeepInfra · 262k, and the most expensive is $1.15 from SambaNova. The largest context window offered is 262k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
DeepInfra · 262k$0.09$0.34262k100.00%
CoreWeave$0.10$0.34262k100.00%
Venice$0.12$0.36256k100.00%
Chutes$0.12$0.37131k96.67%
Crusoe$0.14$0.40262k83.33%
Friendli$0.14$0.40262k100.00%
Novita$0.14$0.40262k43.33%
Parasail$0.15$0.40262k100.00%
DeepInfra · 262k$0.20$0.40262k100.00%
ModelRun$0.75$1.00262k100.00%
SiliconFlow$0.75$1.00262k90.00%
Io Net$0.36$1.09262k86.36%
SambaNova$0.38$1.15131k96.55%