Gemma 4 26B A4B
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 a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.
- Input / 1M tokens
- $0.080
- Output / 1M tokens
- $0.350
- Context window
- 262K tokens
- Provider
- Cached input / 1M
- $0.010
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- —
- Time to first token
- —