Unverified50% confidenceFactExact time
OpenAI's cache hit tokens are typically billed at a 50% discount.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI typically charges 4–6 times more for output tokens than input tokens, because the computation involved in generation far exceeds that of comprehension.73% similarUnverifiedOpenAI dynamically adjusts quotas by account consumption tier (Tier 1 through Tier 5), unlocking higher limits as the account's cumulative spending increases.72% similarVerifiedOpenAI's API billing distinguishes between input tokens and output tokens, with output tokens typically priced higher.72% similarUnverifiedOpenAI has introduced a prompt cache breakpoint mechanism that allows developers to manually specify cache breakpoints, with cache-hit portions typically billed at a discounted rate of 10%–25% of the original price.71% similarUnverifiedOpenAI allows paid users to allocate their entire Token quota to the most powerful version, whereas some competing products impose quota caps on their flagship models.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/926828API
curl https://kongchang.com/api/v1/knowledge/claims/926828MCP
get_claim(id=926828)