Balanced — strong quality at a mid priceCommercial API

Gemma 4 31B (batch) Pricing

Google · google-gemma-4-31b-it-batch

ShareX Facebook LinkedIn

Input / 1M tokens

$0.390

Output / 1M tokens

$0.970

Context window

262,144 tokens

≈ 350 pages of text

Max output

235,929 tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0009

1,000 requests / month$0.856/mo 10,000 requests / month$8.56/mo 100,000 requests / month$85.60/mo

Estimate your own workloadOpens the calculator with Gemma 4 31B (batch) preloaded — adjust volume and token counts there.

Price history

Only one price point recorded so far.

The staircase chart appears once a price change is detected.

What it excels at

Handles extended contexts up to 262k tokens with vision support; cost-effective for batch workloads at $0.39/$0.97 per million tokens.

The business tradeoff

Mid-sized 31B model exhibits noticeable gaps versus frontier systems on complex multi-step reasoning; commercial API availability remains narrower than core Gemini offerings.

Cheaper from Google

Gemini 3.5 Flash Lite (batch)Google$0.0007/ typical request Gemma 4 26B A4BGoogle$0.0001/ typical request

Same tier from other providers

GPT-5.4 MiniOpenAI$0.0027/ typical request Claude Sonnet 4.6Anthropic$0.0096/ typical request Llama 4 MaverickMeta$0.0005/ typical request

Head-to-head

Gemma 4 31B (batch) vs GPT-5.4 Mini →Gemma 4 31B (batch) vs Claude Sonnet 4.6 →Gemma 4 31B (batch) vs Llama 4 Maverick →

Vendor list rates, as of Aug 28, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.