Google: Gemma 4 26B A4B pricing and limits

id google/gemma-4-26b-a4b-it · listed 2026-04-03

Input (per 1M tokens)	$0.076
Output (per 1M tokens)	$0.255
Cached input read (per 1M)	$0.043
Context window	262,144 tokens
Max output	235,929 tokens
Modalities	image+text+video → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.15.

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

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
OpenAI: GPT-6 Luna Pro (batch)	$0.050	$0.250	1,050,000
OpenAI: GPT-6 Luna (batch)	$0.050	$0.250	1,050,000
DeepSeek: DeepSeek V4.1 Flash (batch)	$0.050	$0.150	1,048,576

Other google models

Google: Gemma 4 26B A4B (free) (free / free) · Google: Gemma 4 31B (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: Gemini 2.5 Flash Lite (batch) ($0.050 / $0.200) · Google: Gemma 3 12B ($0.050 / $0.150) · Google: Gemma 3 27B ($0.080 / $0.350)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=google/gemma-4-26b-a4b-it (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