Google: Gemma 4 31B (free) pricing and limits

id google/gemma-4-31b-it:free · listed 2026-04-02

Input (per 1M tokens)	free
Output (per 1M tokens)	free
Context window	262,144 tokens
Max output	32,768 tokens
Modalities	image+text+video → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.00.

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...

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
TypeSafe: Jev Router	$-1000000.000	$-1000000.000	1,000,000
NVIDIA: Switchyard	$-1000000.000	$-1000000.000	1,000,000
OpenRouter: Fusion	$-1000000.000	$-1000000.000	1,000,000

Other google models

Google: Gemma 4 26B A4B (free) (free / free) · Google: Lyria 3 Pro Preview (free / free) · Google: Lyria 3 Clip Preview (free / free) · Google: Gemma 3 4B ($0.040 / $0.050) · Google: Gemma 3 12B ($0.050 / $0.150) · Google: Gemma 3 27B ($0.080 / $0.350) · Google: Gemma 4 26B A4B ($0.090 / $0.300) · Google: Gemini 2.5 Flash Lite ($0.100 / $0.400)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=google/gemma-4-31b-it:free (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=google. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with google. Agent Exchange