Expired50% confidenceEventExact time
In hands-on testing, after building the application and making subsequent adjustments, the account credits dropped from 10 to approximately 3.13, with the vast majority consumed during the initial generation.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/22/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/6/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAccording to the user's test data, the actual resources provided by the new plan are approximately 3 to 6 times less than the previous quota, with the specific magnitude depending on the model used.75% similarUnverified研究表明在INT4/INT8精度下多数推理和生成任务的输出质量下降幅度在1-3%以内66% similarUnverified研究人员发现，仅将函数描述中的retrieve替换为fetch，在某些模型上会导致调用成功率下降约15%65% similarUnverifiedThe researcher empirically measured the quota deduction rate of the old Pro plan by repeatedly calling the /api/usage endpoint before the billing plan switch, with testing covering August 28 to 31 and a margin of error controlled to ±7–13%65% similarUnverifiedIn the software engineering scenario, EvoMem significantly reduced the Regression rate (breaking existing functionality) from approximately 9%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/940334API
curl https://kongchang.com/api/v1/knowledge/claims/940334MCP
get_claim(id=940334)