Google: Gemma 4 26B A4B (free)
Review
The free tier of Google's Gemma 4 26B A4B offers multimodal capability including video input and tool use at no cost, but without benchmark data a conservative score applies; it may be useful for experimentation but businesses should rely on the benchmarked paid version for production use.
Assessment date: April 16, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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..
Capabilities
Architecture
| Modality | Text + Image + Video → Text |
| Tokenizer | Gemma |
| Parameters | 26B |
How does Google: Gemma 4 26B A4B (free) stack up?
Compare side-by-side with other emerging models.
Model Information
| OpenRouter ID |
google/gemma-4-26b-a4b-it:free
|
| Provider | |
| Release Date | April 3, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 32,768 tokens |
| Status | Active |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
