O05: Prompt caching

• Publisher: OpenAI
• URL: Primary source
• Published: not stated
• Updated/version date: not established
• Accessed: 2026-10-22
• Type: official API documentation
• Verification: opened source, rather than relying on a search excerpt

Supported finding

Cache behavior and usage accounting depend on model generation and retention settings. Current documentation includes cache-write fields and charges.

Limits and transfer

Check model-specific pricing, actual cache hits and writes. No universal discount applies to all repeated content.

Use in the session

Mechanism and decision conditions. Retain the qualifications when translating the finding into slide copy. No source establishes Knauf’s savings.