Cached input tokens
Catalog row in Vendor License Metrics · Cited
- Unit
- Other
- Aliases
- Cached input
- Definition
- API list price column "Cached input", per 1M tokens, charged for input tokens served from the prompt cache.
- Counting rules
- Priced per model below the Input rate (for example GPT-6 Sol: Input $2.00, Cached input $0.20 per 1M tokens, Standard, short context, as of 2026-09-26).
- Floors / minimums
- None stated.
- Applies to products
- OpenAI API
- Related metrics
- Product category