Unverified50% confidenceFactExact time
In the usage field of OpenAI Chat Completions, prompt_tokens includes cached tokens (prompt_tokens_details.cached_tokens is a subset of it); when calculating cost, the cached portion must first be subtracted and full price applied to the remainder.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedOpenAI reports cached input tokens in usage.prompt_tokens_details.cached_tokens, and the billing rate is lower; ignoring this causes costs to be overestimated.79% similarVerifiedOpenAI Prompt Caching can reduce the cost of repeated prefixes to 10%–25% of the original price.73% similarUnverifiedCached input tokens are a discount mechanism offered by providers such as OpenAI for large repeated prefixes (such as system prompts, long documents, and few-shot examples); input tokens that hit the cache are billed at a lower rate, usually only about one-tenth of the standard input price.71% similarUnverifiedOpenAI launched the Prompt Caching feature in 2024; when the prompt prefix is completely identical and exceeds the 1,024-token threshold, the KV Cache is reused, and the cached portion is typically billed at 25% of the original price or even lower.71% similarVerifiedPrompt Caching is a cost-optimization mechanism introduced by mainstream LLM providers (such as Anthropic and OpenAI): when the prefix portion of multiple requests is completely identical, the provider caches that portion of the computation, and tokens that hit the cache are billed at a price far below normal input.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1051979API
curl https://kongchang.com/api/v1/knowledge/claims/1051979MCP
get_claim(id=1051979)