Unverified50% confidenceFactExact time
Retrieval budget usually refers to the number of documents allowed to be retrieved in a single question-answering session, the upper limit of recalled passages, or the token capacity of the context window.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe context window refers to the maximum number of tokens a single request can hold (input plus output); the larger the window, the higher the cost per call.68% similarUnverifiedThe token quota is a ceiling and the budget is a plan; the two are different, and usage reporting is optional in practice—some responses carry a usage block and some carry none at all.68% similarUnverified实践中通过设置「上下文预算」为每次模型调用设定 token 上限，并在预算内通过优先级排序决定包含哪些信息67% similarVerifiedThinking tokens for reasoning models are typically billed, and setting a token budget cap can prevent runaway costs from a single request.67% similarUnverifiedAnthropic's long-context pricing documentation states that requests exceeding the threshold are billed at the higher price even if part of the prompt hits the cache.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079369API
curl https://kongchang.com/api/v1/knowledge/claims/1079369MCP
get_claim(id=1079369)