LLMCost
google

Google: Gemma 4 31B API Pricing

Google: Gemma 4 31B costs $0.100 per 1M input tokens and $0.340 per 1M output tokens (cache reads: $0.100). Context window: 262K. Prices verified 2026-08-23 Β· source

Input / 1M tokens
$0.100
Output / 1M tokens
$0.340
Context window
262K
Max output
262K

What would Google: Gemma 4 31B cost you per month?

WorkloadRequests/moAvg tokens (in/out)Est. monthly cost
Light chatbot10,000800 / 400$2.16
Coding agent5,0008,000 / 2,000$7.40
RAG pipeline30,0004,000 / 500$17.10
Doc summarizer2,00020,000 / 1,000$4.68

Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.

About Google: Gemma 4 31B

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...

Compare Google: Gemma 4 31B with

Official resources