Gemma 4 26B A4B (free)
GOOGLE Developer Architecture Profile
Intelligence (ELO)1212Chatbot Arena Verified
Max Context262,144Tokens
API Cost / 1MFREEBlended Prompt + Completion
Model Capabilities
- Top Tier
- Coding & Logic
- Fictional
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...
Granular Pricing Matrix
Input Tokens (Prompt)Free / 1M
Output Tokens (Completion)Free / 1M
Pricing data via OpenRouter. Sync: 4/7/2026