News tagged "cost"

Editorial illustration of a gateway routing layer inspecting a prompt cache miss report, showing diagnostic reason codes in a clean newsroom style.

OpenAI Prompt Cache Diagnostics Is GA: What Gateway Operators Must Not Strip

OpenAI's Prompt Cache Diagnostics tool is now GA in the Responses API. It adds comparison_response_id and a reason field that explain cache misses—and breaks silently if your AI gateway strips prompt_cache_options.

September 13, 2026via OpenAI

Abstract editorial illustration of a routing gateway receiving cached prompt prefixes from a cloud provider, with a 24-hour retention clock symbol in a minimal newsroom style.

openai

OpenAI Prompt Cache Retention Defaults to 24h: GPT-5.5 and API Routing Impact

OpenAI now defaults eligible GPT-5 prompt cache retention to 24h for non-ZDR organizations. Learn how GPT-5.5, prompt_cache_key, and gateway routing choices affect API cost and data policy.

June 4, 2026via OpenAI