Expired95% confidenceFactTime unknown
Coding Plan uses a per-request billing model rather than per-token billing, counting each request as 1 regardless of how many tokens it carries.
1
Sources
95%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
VerifiedIn API billing, the unit price of output tokens is generally higher than that of input tokens, because the generation process requires autoregressive inference token by token68% similarUnverifiedClaude Code's API billing typically prices input tokens and output tokens separately; the linear accumulation of input tokens across conversation turns is the primary driver of cost inflation in long tasks.67% similarUnverifiedPrompt Caching在提示词前缀完全相同且超过约1024 token阈值时命中，缓存token通常按原价的25%甚至更低计费66% similarUnverifiedThis pay-as-you-go plan states that the plugin is only responsible for account rotation and usage recording, and does not modify any code in the Cursor software itself.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13422API
curl https://kongchang.com/api/v1/knowledge/claims/13422MCP
get_claim(id=13422)