Workers AI runs inference for Moonshot's Kimi K-series and Z.ai's GLM models on GPUs in Cloudflare data centers. These models are large, long-context, and mixture-of-experts types, presenting challenges in efficient serving due to memory constraints.

Nano Banana 2 Lite offers dramatically reduced latency for image generation and editing. This model provides high-speed performance at a lower cost, allowing users to generate thousands of images efficiently while maintaining character consistency and accuracy.

Gemma 4 has introduced Multi-Token Prediction (MTP) to enhance inference speed. New checkpoints optimized with Quantization-Aware Training (QAT) have been released to improve efficiency for mobile and laptop use.

Gemma 4 now features Multi-Token Prediction (MTP) drafters, enhancing inference speed and efficiency. This update aims to improve performance across developer workstations, mobile devices, and cloud environments.

The universal CLAUDE.md file reduces Claude's output verbosity by approximately 63% without requiring any code changes. While it primarily addresses output behavior, most costs associated with Claude stem from input tokens rather than output.