Unverified50% confidenceFactExact time
Token generation is billed by consumption; if an application requests a 4,000-token completion and the user stops after the 100th token, failure to propagate the cancellation signal means paying for the remaining 3,900 unrendered tokens.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEach retry resends the complete prompt input tokens and is billed in full; a request with 4,000 input tokens retried 3 times will consume 16,000 tokens.73% similarUnverifiedThe tester noted: Cursor did not report cache-write tokens, so its true token consumption is very likely higher than 92,000.72% similarUnverifiedToken consumption is paused while the watchdog waits—it is only polling API status and incurs no additional cost; failed retries, by contrast, may consume more tokens because the context is sent repeatedly.71% similarUnverifiedWhen a streaming response is interrupted midway, the portion of output tokens already generated is still billed, even though the client may not have received the complete result.71% 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69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033727API
curl https://kongchang.com/api/v1/knowledge/claims/1033727MCP
get_claim(id=1033727)