Intelligence Index
0125.7
> 57% OF MODELS
Google
Gemma 4 26B A4B
Updated: June 2026
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...
Specifications
- Context
- 262K
- Input
- $0.06/M
- Output
- $0.33/M
Capabilities
VISIONTEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Gemma 3n 4B | Google | 33K | $0.06/M | $0.12/M |
| Qwen3 8B | Qwen | 131K | $0.05/M | $0.4/M |
| Gemma 3 4B | Google | 131K | $0.05/M | $0.1/M |
| Gemma 3 12B | Google | 131K | $0.05/M | $0.15/M |
| Mistral Small 3 | MistralAI | 33K | $0.05/M | $0.08/M |
Performance Metrics
Coding Index
0222.4
> 47% OF MODELS
Agentic Index
0332.1
> 54% OF MODELS
DATA SOURCE: Artificial Analysis