Expired50% confidenceFactExact time
Input tokens now account for more than 90% of total non-cached tokens, and the cost share of input context has risen from 47.5% to nearly 70%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedIn intelligent programming scenarios, input tokens often account for more than 80% of total consumption.78% similarUnverifiedCache-read tokens account for more than 90% of overall token activity.77% similarUnverifiedThe Prompt Caching mechanism can typically save 50%–90% of input costs.75% similarVerifiedMajor vendors commonly adopt differentiated pricing for input tokens and output tokens, with output tokens typically costing 3–5 times more than input tokens.70% similarUnverifiedThe Prompt Caching mechanism can reuse the KV Cache of identical prefix contexts, typically reducing input token costs by 50%–90%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/50715API
curl https://kongchang.com/api/v1/knowledge/claims/50715MCP
get_claim(id=50715)