TokenCosts AI.iov1.0
Back to Models Directory
Googlegemma-4-26b-a4b-it

Google: Gemma 4 26B A4B API Pricing

Official PricingCall via OpenRouter

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 q...

Base Input Price$0.076/ 1M tokens
Base Output Price$0.26/ 1M tokens
Prompt Cache Read$0.043-44.44% discount
Batch API Rate-50%24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
Google Direct$0.076$0.26SupportedConnect
OpenRouter$0.076$0.26SupportedConnect

Head-to-Head Comparisons for Google: Gemma 4 26B A4B

Google: Gemma 4 26B A4B vs OpenAI: GPT-6.1 Sol$0.0765/M vs $2/M
Google: Gemma 4 26B A4B vs GPT-4o (Omni)$0.0765/M vs $2.5/M
Google: Gemma 4 26B A4B vs Claude 3.5 Sonnet$0.0765/M vs $3/M
Google: Gemma 4 26B A4B vs DeepSeek-V3 (deepseek-chat)$0.0765/M vs $0.27/M