LICENSEWARE
OpenAI Metric

Cache writes

Catalog row in Vendor License Metrics · Cited

Unit
Other
Definition
API list price column "Cache writes", per 1M tokens, shown for the GPT-6 flagship models alongside Input, Cached input and Output.
Counting rules
Priced per model (for example GPT-6 Sol: Cache writes $2.50 per 1M tokens, Standard, short context, as of 2026-09-26).
Floors / minimums
None stated.
Applies to products
  • OpenAI API
Product category
Esc