Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | googleGoogle: Gemma 4 26B A4BRemove × |
|---|---|
| What’s different | 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... |
| Date | Mar 11, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.042 in / $0.22 out/ 1M tokensDarkbloom · via OpenRouter · all routes ↗darkbloom |
| Provider endpoints | 19 endpoints → |
Specifications | |
| Context window | 262.1K |
| Max output | 235.9K |
| Parameters | 26B |
| Tool calling | Supported |
| Structured output | Supported |
| Image input | Supported |
| Video input | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |