Groq adds automatic prompt caching to openai/gpt-oss-20b

AI Impact Summary

Groq has introduced automatic prompt caching for the openai/gpt-oss-20b model, offering significant cost savings (50%) and reduced latency through reuse of computation. This capability automatically activates for all users without any configuration changes, streamlining the inference process and improving performance. This update represents a key enhancement to the model's efficiency and responsiveness.